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

    Neuronpedia

    INDEX
    Explanations

    am

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    满分
    -0.07
     eleg
    -0.07
     ANAL
    -0.07
     Dana
    -0.07
     DR
    -0.06
     Rebecca
    -0.06
     Gregory
    -0.06
     steak
    -0.06
     Def
    -0.06
     Świat
    -0.06
    POSITIVE LOGITS
    hare
    0.07
    /weather
    0.07
    查阅
    0.07
    �
    0.07
    맨
    0.06
    ⴰ
    0.06
    Ѵ
    0.06
    哄
    0.06
     psychiatrist
    0.06
    โคร
    0.06
    Act Density 0.064%

    No Known Activations