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

    Neuronpedia

    INDEX
    Explanations

    disclaimers and warnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lacks
    -0.08
     её
    -0.07
    간
    -0.07
    =="
    -0.07
    ชาต
    -0.07
     Hour
    -0.07
    英国
    -0.07
    !!!↵↵
    -0.07
     иг
    -0.06
     Selection
    -0.06
    POSITIVE LOGITS
    über
    0.06
    PreparedStatement
    0.06
     chez
    0.06
    .decoder
    0.06
    Old
    0.06
     cryst
    0.06
    mm
    0.06
    lášení
    0.05
    міну
    0.05
    ザ
    0.05
    Act Density 0.026%

    No Known Activations