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

    Neuronpedia

    INDEX
    Explanations

    intense descriptors that indicate significant changes or differences

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

    dramatic improvements or striking differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageTagHelper
    -0.54
    IntoConstraints
    -0.54
    AddTagHelper
    -0.52
    AnchorStyles
    -0.47
    InputTagHelper
    -0.47
    Parcelize
    -0.45
    AnchorTagHelper
    -0.45
    EndInit
    -0.44
    contentLoaded
    -0.43
    fjspx
    -0.41
    POSITIVE LOGITS
    contrast
    0.63
     contraste
    0.61
     dramatic
    0.59
     contrast
    0.58
    vivid
    0.57
     Dramatic
    0.57
     spectacular
    0.57
     contrasts
    0.56
     Contrast
    0.55
     výraz
    0.55
    Act Density 0.162%

    No Known Activations