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

    Neuronpedia

    INDEX
    Explanations

    terms and conditions related to mathematical structures and properties

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

    non-zero or non-trivial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Frau
    -0.44
    haviour
    -0.44
     ModelRenderer
    -0.43
     grounding
    -0.43
     Esper
    -0.42
    havior
    -0.42
     COMPUT
    -0.42
     Herd
    -0.41
     Reina
    -0.41
     Casper
    -0.41
    POSITIVE LOGITS
    transQ
    0.52
    IsMutable
    0.50
    setVerticalGroup
    0.48
     purpoſe
    0.46
    tanleria
    0.44
    notEmpty
    0.43
     ProtoMessage
    0.42
    autoIncrement
    0.40
     houſe
    0.40
     незавершена
    0.39
    Act Density 0.297%

    No Known Activations