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

    Neuronpedia

    INDEX
    Explanations

    references to internal cognitive processes and their influences on behavior

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

    representing causal relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.64
     surla
    -0.61
     ProtoMessage
    -0.59
    LookAnd
    -0.56
    出版年
    -0.55
    Pyx
    -0.54
     BoxFit
    -0.54
     sentada
    -0.52
     AssemblyVersion
    -0.52
     CreateTagHelper
    -0.52
    POSITIVE LOGITS
     aud
    0.40
     iso
    0.40
     supers
    0.39
     ujednoznacz
    0.37
    ',['
    0.36
    aud
    0.35
    AUD
    0.35
     Brus
    0.34
     AUD
    0.34
    endregion
    0.34
    Act Density 0.024%

    No Known Activations