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

    Neuronpedia

    INDEX
    Explanations

    instances of negation or denial

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

    possessive apostrophes and contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.59
     Winaray
    -0.57
     SwitchCompat
    -0.56
    Autoritní
    -0.54
    ChildScrollView
    -0.54
     onCreateView
    -0.54
     Defendants
    -0.52
     كومونز
    -0.52
    GRect
    -0.51
    Demografie
    -0.50
    POSITIVE LOGITS
     Их
    0.40
    enumi
    0.36
    enumii
    0.36
     afge
    0.34
     narrator
    0.34
     perſon
    0.34
     writer
    0.32
    ผู้
    0.32
     getF
    0.32
    Their
    0.31
    Act Density 0.033%

    No Known Activations