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

    Neuronpedia

    INDEX
    Explanations

    ary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'ya
    -0.07
     Resort
    -0.06
     gimm
    -0.06
    曲
    -0.06
     Sword
    -0.06
     Svg
    -0.06
     prefix
    -0.06
    ":"
    -0.06
     Ve
    -0.06
    audit
    -0.06
    POSITIVE LOGITS
    xBA
    0.07
    _PRIVATE
    0.07
     어려
    0.07
     Beginners
    0.06
    精品
    0.06
     اهم
    0.06
    .DropTable
    0.06
     万元
    0.06
    ah
    0.06
    normalized
    0.06
    Act Density 0.001%

    No Known Activations