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

    Neuronpedia

    INDEX
    Explanations

    personal judgement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     glu
    -0.07
     parsley
    -0.07
     Westbrook
    -0.07
    (hidden
    -0.07
     storytelling
    -0.07
    continental
    -0.07
     Bakan
    -0.07
    ลม
    -0.07
     }],↵
    -0.07
    ולוג
    -0.07
    POSITIVE LOGITS
    防
    0.07
    .break
    0.07
    😖
    0.07
     Debt
    0.06
    辩
    0.06
    _blank
    0.06
     eas
    0.06
    _sent
    0.06
    判
    0.06
    不合理
    0.06
    Act Density 0.053%

    No Known Activations