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

    Neuronpedia

    INDEX
    Explanations

    ker

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     editions
    -0.07
    assis
    -0.07
    itles
    -0.07
    鋼
    -0.06
    шу
    -0.06
    shall
    -0.06
    Inicio
    -0.06
    ictionary
    -0.06
    -chain
    -0.06
     пример
    -0.06
    POSITIVE LOGITS
     broadcast
    0.07
     g
    0.06
    私
    0.06
     combining
    0.06
    $('.
    0.06
     audi
    0.06
     styling
    0.06
     псих
    0.06
     Jerry
    0.06
     erst
    0.06
    Act Density 0.001%

    No Known Activations