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

    Neuronpedia

    INDEX
    Explanations

    Plot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (NS
    -0.07
     уже
    -0.07
     HC
    -0.07
    姐姐
    -0.07
    .propTypes
    -0.06
    Agents
    -0.06
    铷
    -0.06
    EE
    -0.06
     epilepsy
    -0.06
    Numeric
    -0.06
    POSITIVE LOGITS
    改革开放
    0.07
     מקום
    0.07
    Washington
    0.07
     Door
    0.07
     ("%
    0.06
    /blog
    0.06
    髮
    0.06
     Opening
    0.06
     diploma
    0.06
    愉悦
    0.06
    Act Density 0.001%

    No Known Activations