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

    Neuronpedia

    INDEX
    Explanations

    OC

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     області
    -0.07
    riculum
    -0.07
    evil
    -0.07
     stolen
    -0.06
     believe
    -0.06
     باد
    -0.06
     physique
    -0.06
    leriyle
    -0.06
    nbsp
    -0.06
     musicians
    -0.06
    POSITIVE LOGITS
    _or
    0.07
    �
    0.07
     ukaz
    0.07
    .Av
    0.06
    'я
    0.06
    /O
    0.06
     가정
    0.06
    .Once
    0.06
     Om
    0.06
     ок
    0.06
    Act Density 0.017%

    No Known Activations