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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *angstrom
    -0.07
    叙
    -0.07
    ogo
    -0.07
     Polyester
    -0.07
    㤘
    -0.06
    -cmpr
    -0.06
     domic
    -0.06
    白云
    -0.06
    Fax
    -0.06
    CAS
    -0.06
    POSITIVE LOGITS
    出来
    0.07
    Crystal
    0.07
    悩
    0.07
    орт
    0.07
    ッシュ
    0.07
    inox
    0.06
    Way
    0.06
    control
    0.06
     Rid
    0.06
    .Term
    0.06
    Act Density 0.026%

    No Known Activations