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

    Neuronpedia

    INDEX
    Explanations

    specific LaTeX math syntaxes and notation

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

    Subscripts, especially "in" and "ex"

    np_acts-logits-general · gemini-2.0-flash

    external or internal loss rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.74
    resizingMask
    -0.71
    ſelves
    -0.71
     ſein
    -0.70
    majánló
    -0.69
     Verſ
    -0.68
     Beſ
    -0.68
     Geiſt
    -0.68
     desmotivaciones
    -0.67
    rungsseite
    -0.66
    POSITIVE LOGITS
    s
    0.54
    C
    0.47
    H
    0.44
    A
    0.43
    {
    0.43
    O
    0.41
    S
    0.41
    a
    0.38
    R
    0.38
    x
    0.37
    Act Density 0.248%

    No Known Activations