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

    Neuronpedia

    INDEX
    Explanations

    content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     модель
    -0.07
    俘
    -0.07
    iddled
    -0.06
    atile
    -0.06
    院副院长
    -0.06
     pagamento
    -0.06
    盲
    -0.06
     Ambient
    -0.06
    فل
    -0.06
     minority
    -0.06
    POSITIVE LOGITS
     begins
    0.08
    עלות
    0.08
    泰安
    0.07
     Immun
    0.07
    规划设计
    0.06
    作了
    0.06
    仍在
    0.06
    Compar
    0.06
     들어
    0.06
     arrow
    0.06
    Act Density 0.003%

    No Known Activations