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

    Neuronpedia

    INDEX
    Explanations

    part

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aec
    -0.07
    楽
    -0.06
    importe
    -0.06
     Bahrain
    -0.06
     Beaver
    -0.06
     Beijing
    -0.06
     younger
    -0.06
     interracial
    -0.06
     abych
    -0.06
     belir
    -0.06
    POSITIVE LOGITS
     squeeze
    0.07
     blatant
    0.07
    "%(
    0.07
    ‌شد
    0.07
    razy
    0.07
    ista
    0.06
     klid
    0.06
    queeze
    0.06
     temiz
    0.06
    َج
    0.06
    Act Density 0.000%

    No Known Activations