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

    Neuronpedia

    INDEX
    Explanations

    code comment separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mess
    -0.76
     Ancestry
    -0.75
     cij
    -0.72
    culada
    -0.72
     hopeless
    -0.69
     Prou
    -0.69
     Shoreline
    -0.69
    ブリッド
    -0.66
     Mess
    -0.66
    lido
    -0.66
    POSITIVE LOGITS
    fá
    0.71
    ikal
    0.69
    tarta
    0.66
    baijan
    0.66
    Delegate
    0.66
     dirigir
    0.64
     празд
    0.63
    aughty
    0.63
    Clare
    0.63
     Substitute
    0.62
    Act Density 0.082%

    No Known Activations