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

    Neuronpedia

    INDEX
    Explanations

    expressions of absolute or emphatic descriptions

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

    unqualified states and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    béco
    -0.57
    ">//
    -0.56
    writeFieldEnd
    -0.50
    叶修
    -0.46
    IVEREF
    -0.46
     дописавши
    -0.45
     remer
    -0.45
     VizieR
    -0.44
    hical
    -0.44
     OFDb
    -0.44
    POSITIVE LOGITS
     outright
    0.84
     downright
    0.80
     pure
    0.65
     straightforward
    0.56
    pure
    0.56
     Pure
    0.52
    Pure
    0.49
     absolute
    0.49
     StatelessWidget
    0.48
    PURE
    0.48
    Act Density 0.041%

    No Known Activations