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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ificador
    -0.07
     Orlando
    -0.07
     __
    -0.07
     Moodle
    -0.07
    刑法
    -0.07
    
    -0.07
    桹
    -0.07
    遏
    -0.06
     you
    -0.06
     under
    -0.06
    POSITIVE LOGITS
     passionate
    0.07
     giản
    0.07
    ек
    0.07
    *h
    0.07
    resar
    0.07
    .bz
    0.07
    erson
    0.07
    改动
    0.07
    Kn
    0.07
    אהבה
    0.07
    Act Density 0.007%

    No Known Activations