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

    Neuronpedia

    INDEX
    Explanations

    oral anatomy and function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    مة
    0.97
    ită
    0.93
    0.91
    ༡
    0.88
     motionless
    0.84
     muškar
    0.83
    pictureBox
    0.82
    ozione
    0.81
    áli
    0.81
     филосо
    0.79
    POSITIVE LOGITS
    ;
    0.92
    h
    0.87
    "
    0.86
    ти
    0.79
     as
    0.76
    a
    0.76
     or
    0.73
    iden
    0.73
    р
    0.72
    น
    0.72
    Act Density 0.003%

    No Known Activations