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

    Neuronpedia

    INDEX
    Explanations

    code/data/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coy
    -0.07
    063
    -0.07
    acente
    -0.06
     بنابر
    -0.06
    .No
    -0.06
    101
    -0.06
    阅读次数
    -0.06
    .Ag
    -0.06
    hiba
    -0.06
    ثار
    -0.06
    POSITIVE LOGITS
     phot
    0.07
     Ginger
    0.07
     usar
    0.07
    oto
    0.06
     определ
    0.06
    明
    0.06
    ند
    0.06
     desenv
    0.06
     philanth
    0.06
     मजब
    0.06
    Act Density 0.000%

    No Known Activations