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
    bagai
    -0.07
    Chance
    -0.06
     должен
    -0.06
    .foreach
    -0.06
     Matching
    -0.06
    ители
    -0.06
    acts
    -0.06
     bananas
    -0.06
     prey
    -0.06
    /INFO
    -0.06
    POSITIVE LOGITS
     hp
    0.07
    607
    0.06
    603
    0.06
    َد
    0.06
     Ion
    0.06
    671
    0.06
    貴
    0.06
    function
    0.06
    ศร
    0.06
    /Admin
    0.06
    Act Density 0.012%

    No Known Activations