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

    Neuronpedia

    INDEX
    Explanations

    programming/technical terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     multiple
    -0.06
    (hidden
    -0.06
     Iterate
    -0.06
     iterate
    -0.06
    Alias
    -0.06
     рук
    -0.06
     binder
    -0.06
    pis
    -0.06
    iterate
    -0.06
     않을
    -0.06
    POSITIVE LOGITS
     REC
    0.07
    'gc
    0.06
    께서
    0.06
    .clearRect
    0.06
     वन
    0.06
    _SMS
    0.06
     Кал
    0.06
    ştir
    0.06
    ymoon
    0.06
     غير
    0.06
    Act Density 0.897%

    No Known Activations