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

    Neuronpedia

    INDEX
    Explanations

    Technical documentation/articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    寒
    -0.07
    /arm
    -0.07
    禁
    -0.07
    湔
    -0.07
    .route
    -0.06
     pick
    -0.06
    托管
    -0.06
     denote
    -0.06
     bowel
    -0.06
    _check
    -0.06
    POSITIVE LOGITS
     Mills
    0.09
    本能
    0.08
     protesting
    0.07
    全国人民
    0.07
    ent
    0.07
    忘记了
    0.07
    ياة
    0.07
    ủa
    0.07
    ائهم
    0.06
     PCs
    0.06
    Act Density 0.069%

    No Known Activations