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

    Neuronpedia

    INDEX
    Explanations

    License

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    嗳
    -0.08
    memo
    -0.07
    栏
    -0.07
    
    -0.07
    دافع
    -0.07
    靺
    -0.07
     Madd
    -0.06
    inant
    -0.06
     э
    -0.06
    —all
    -0.06
    POSITIVE LOGITS
     districts
    0.08
    generator
    0.07
    州市
    0.07
     американ
    0.07
    琰
    0.07
    .library
    0.07
     continuity
    0.07
     attrib
    0.07
     Nature
    0.07
     Deploy
    0.07
    Act Density 0.000%

    No Known Activations