Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and their representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "[something] can be written/expressed as"

    np_acts-logits-general · gemini-2.0-flash

    how things are written or decomposed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cshtml
    -0.56
    AddTagHelper
    -0.54
    principalColumn
    -0.53
    CopyWith
    -0.53
    bitField
    -0.52
    ($__
    -0.52
    วย
    -0.51
    fony
    -0.48
     deleteById
    -0.48
    UIControlState
    -0.47
    POSITIVE LOGITS
     rewrite
    0.65
     decomposition
    0.63
     decompose
    0.61
     desg
    0.59
     write
    0.58
    Begriffsklä
    0.58
     representation
    0.58
     decom
    0.57
     écrit
    0.57
     Representation
    0.56
    Act Density 0.779%

    No Known Activations