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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     champs
    -0.08
     Pays
    -0.08
    暑
    -0.07
    ≌
    -0.07
    理想信念
    -0.07
     compensated
    -0.07
    tz
    -0.07
     najczęściej
    -0.07
    将会
    -0.07
    .Selenium
    -0.07
    POSITIVE LOGITS
    (",",
    0.07
     colabor
    0.07
    阿拉
    0.07
    铌
    0.06
    てきて
    0.06
     [],↵
    0.06
    仪器
    0.06
     numberOf
    0.06
     Screw
    0.06
    .lb
    0.06
    Act Density 0.001%

    No Known Activations