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

    Neuronpedia

    INDEX
    Explanations

    Mirror

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cake
    -0.07
    .What
    -0.07
     závě
    -0.07
    .ToArray
    -0.07
     �
    -0.06
    unprocessable
    -0.06
    fony
    -0.06
    Ubuntu
    -0.06
    prepared
    -0.06
    逐
    -0.06
    POSITIVE LOGITS
     Wheeler
    0.06
    paginator
    0.06
     نگهداری
    0.06
    -viol
    0.06
    历史
    0.06
     Haiti
    0.06
     emitter
    0.06
    Mirror
    0.06
    lear
    0.06
    _mgr
    0.06
    Act Density 0.000%

    No Known Activations