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

    Neuronpedia

    INDEX
    Explanations

    Separating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GetMethod
    -0.06
    545
    -0.06
    Endpoint
    -0.06
    请
    -0.06
    .gridColumn
    -0.06
     interpolation
    -0.06
     contradictory
    -0.06
    _stock
    -0.06
     justify
    -0.06
     lateinit
    -0.05
    POSITIVE LOGITS
     muff
    0.07
    �
    0.07
     έν
    0.07
    "%(
    0.07
     Εν
    0.07
    prav
    0.07
    χα
    0.06
    ักก
    0.06
    沙
    0.06
    κε
    0.06
    Act Density 0.024%

    No Known Activations