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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    י�
    -0.07
     instit
    -0.06
     mouth
    -0.06
     avocado
    -0.06
    еф
    -0.06
    _closure
    -0.06
     supper
    -0.06
     citizenship
    -0.06
    idia
    -0.06
    .birth
    -0.06
    POSITIVE LOGITS
    397
    0.07
     photograph
    0.07
     ще
    0.07
    Noise
    0.06
    ================================
    0.06
    road
    0.06
    _MIC
    0.06
    .+
    0.06
    /***************************************************************************↵
    0.06
    響
    0.06
    Act Density 0.005%

    No Known Activations