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

    Neuronpedia

    INDEX
    Explanations

    metrics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ˒
    -0.07
     """",↵
    -0.07
     messing
    -0.06
    "",↵
    -0.06
    %↵
    -0.06
    万余
    -0.06
    崄
    -0.06
     ]
↵
    -0.06
    ']],↵
    -0.06
    돐
    -0.06
    POSITIVE LOGITS
    lığı
    0.07
    למיד
    0.07
    ę
    0.07
     İçin
    0.07
    gebn
    0.07
    arga
    0.07
     występ
    0.07
     Birmingham
    0.07
    liches
    0.07
    фикс
    0.06
    Act Density 0.001%

    No Known Activations