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
    (rp
    -0.07
    μεν
    -0.07
    	pos
    -0.06
    adratic
    -0.06
    rail
    -0.06
    最
    -0.06
    ्पर
    -0.06
     گونه
    -0.06
    мо
    -0.06
    一度
    -0.06
    POSITIVE LOGITS
     Chick
    0.07
    _EXIST
    0.07
    ея
    0.06
    上げ
    0.06
    icontains
    0.06
     Commit
    0.06
    _CHOICES
    0.06
     ##
    0.06
    .GetInt
    0.06
     MCC
    0.06
    Act Density 0.004%

    No Known Activations