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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wool
    -0.06
     AJAX
    -0.06
    _win
    -0.06
    cial
    -0.06
    wegian
    -0.06
     ceremonial
    -0.06
    host
    -0.06
    -linear
    -0.06
    ordin
    -0.06
    üven
    -0.06
    POSITIVE LOGITS
     uz
    0.07
    したら
    0.07
    .argsort
    0.07
     istediğiniz
    0.07
     SUB
    0.06
    =__
    0.06
     HI
    0.06
    (hit
    0.06
     усл
    0.06
     ö
    0.06
    Act Density 0.035%

    No Known Activations