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

    Neuronpedia

    INDEX
    Explanations

    names or titles followed by dashes or punctuation

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

    names or introductory phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rítica
    -0.46
    orate
    -0.45
    phazard
    -0.45
     typelib
    -0.44
    iettivo
    -0.43
    uxxxx
    -0.42
    gnore
    -0.40
    nabis
    -0.40
    utile
    -0.40
    dott
    -0.40
    POSITIVE LOGITS
     Bewußt
    0.48
    AnimationsModule
    0.45
    Selfer
    0.45
    OGND
    0.45
    AutoField
    0.45
    ❋
    0.42
    BufferException
    0.42
     varandra
    0.39
     PopupWindow
    0.38
    SuspendLayout
    0.37
    Act Density 0.034%

    No Known Activations