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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     identities
    -0.06
    (which
    -0.06
     мон
    -0.06
    _('
    -0.06
    くな
    -0.06
     ска
    -0.06
     cases
    -0.06
    uably
    -0.06
    (layout
    -0.06
     summed
    -0.06
    POSITIVE LOGITS
    =context
    0.07
    IRS
    0.07
    erior
    0.07
    bis
    0.07
     counselor
    0.06
    روع
    0.06
    영
    0.06
    -office
    0.06
    (connectionString
    0.06
    	Iterator
    0.06
    Act Density 0.000%

    No Known Activations