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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and their definitions

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

    Followed by a mathematical symbol

    np_acts-logits-general · gemini-2.0-flash

    Let us

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.81
     tartalomajánló
    -0.78
    principalColumn
    -0.77
     BoxFit
    -0.74
    WriteBarrier
    -0.73
    EndGlobalSection
    -0.70
    AsUp
    -0.69
     ModelExpression
    -0.69
     BorderRadius
    -0.69
    retudo
    -0.68
    POSITIVE LOGITS
     $
    0.65
     again
    0.60
     $\
    0.59
     R
    0.51
    förder
    0.51
     K
    0.50
     ${\
    0.49
     denote
    0.49
     B
    0.48
    again
    0.48
    Act Density 0.813%

    No Known Activations