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

    Neuronpedia

    INDEX
    Explanations

    longitudinal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pa
    -0.07
    层
    -0.07
    .From
    -0.07
    린
    -0.07
     islands
    -0.07
    卖给
    -0.07
    税
    -0.07
    胥
    -0.07
    _corr
    -0.07
    輸
    -0.07
    POSITIVE LOGITS
    国内外
    0.07
     enorm
    0.07
    houette
    0.07
     Experience
    0.06
     בנוגע
    0.06
    初三
    0.06
    pn
    0.06
     Confirmation
    0.06
    angular
    0.06
     anale
    0.06
    Act Density 0.037%

    No Known Activations