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

    Neuronpedia

    INDEX
    Explanations

    dissoci

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    镧
    -0.07
    'class
    -0.07
    .Clone
    -0.07
    Inc
    -0.07
    갈
    -0.07
    voices
    -0.07
    Scalars
    -0.06
    实
    -0.06
    ("**
    -0.06
     Madonna
    -0.06
    POSITIVE LOGITS
    蜜
    0.07
    ポイント
    0.07
    -urlencoded
    0.07
    ZY
    0.07
     Sensors
    0.07
     -=
    0.06
    .Registry
    0.06
    に対して
    0.06
     shred
    0.06
     IPT
    0.06
    Act Density 0.001%

    No Known Activations