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

    Neuronpedia

    INDEX
    Explanations

    home

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Marshal
    -0.07
     міс
    -0.07
     возраст
    -0.06
     bloss
    -0.06
    _variables
    -0.06
     diam
    -0.06
     питань
    -0.06
     Час
    -0.06
     dimensions
    -0.06
     stirring
    -0.06
    POSITIVE LOGITS
    े,
    0.07
     imply
    0.07
    ined
    0.07
     PROF
    0.07
     ait
    0.07
    정이
    0.07
     Enables
    0.06
     Superman
    0.06
    iştir
    0.06
    ITY
    0.06
    Act Density 0.002%

    No Known Activations