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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinions or statements

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

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kohta
    -0.30
     предо
    -0.28
     juuri
    -0.27
     heterogeneous
    -0.27
     mín
    -0.26
    LineNumber
    -0.25
     Auß
    -0.25
     nzuri
    -0.25
     Fros
    -0.25
     interval
    -0.25
    POSITIVE LOGITS
     retired
    0.81
    retired
    0.77
    Retired
    0.77
    parsedMessage
    0.69
    хьтан
    0.69
     Retired
    0.68
    SourceChecksum
    0.65
    RefNanny
    0.63
     noDo
    0.63
    ScopeManager
    0.61
    Act Density 0.120%

    No Known Activations