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

    Neuronpedia

    INDEX
    Explanations

    code/data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     concession
    -0.07
     selector
    -0.06
    	DEBUG
    -0.06
     TERMIN
    -0.06
     rent
    -0.06
    doch
    -0.06
     заклад
    -0.06
     propulsion
    -0.06
    ,data
    -0.06
     Sele
    -0.06
    POSITIVE LOGITS
    ẩy
    0.07
     sophomore
    0.07
    toFixed
    0.07
    уванні
    0.07
    自由
    0.06
    .gt
    0.06
    _validation
    0.06
     privileges
    0.06
    .php
    0.06
     vữ
    0.06
    Act Density 0.023%

    No Known Activations