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

    Neuronpedia

    INDEX
    Explanations

    terms related to influence and authority

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

    attributes and constraints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.63
    stylers
    -0.43
    يميديا
    -0.42
    mogat
    -0.41
     Италијани
    -0.38
     Italijanski
    -0.37
    ++]
    -0.37
    writerow
    -0.36
    LayoutStyle
    -0.36
     ролях
    -0.36
    POSITIVE LOGITS
    RegressionTest
    0.48
    InstrumentedTest
    0.44
    ApiModelProperty
    0.43
     nakalista
    0.40
     makeStyles
    0.40
    offsetof
    0.39
    0.39
    ->___
    0.38
    JSONException
    0.38
     tatt
    0.37
    Act Density 0.055%

    No Known Activations