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
     Plans
    -0.07
     gradients
    -0.07
     anarchist
    -0.07
     tre
    -0.07
     iterations
    -0.07
     invol
    -0.07
    cales
    -0.06
     بعدی
    -0.06
    .Reference
    -0.06
     synthesis
    -0.06
    POSITIVE LOGITS
    ->↵
    0.07
    (repository
    0.07
    �断
    0.06
    turn
    0.06
    opup
    0.06
    apGestureRecognizer
    0.06
     Pod
    0.06
    पन
    0.06
     привед
    0.06
    ालत
    0.06
    Act Density 0.175%

    No Known Activations