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

    Neuronpedia

    INDEX
    Explanations

    quantities and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    嫻
    -0.78
    ーキング
    -0.71
    chets
    -0.71
     ચ
    -0.69
    utete
    -0.68
    ši
    -0.68
    engar
    -0.67
    🍶
    -0.66
    typeorm
    -0.66
    DAV
    -0.66
    POSITIVE LOGITS
     milliers
    1.00
     Gall
    0.89
     hundreds
    0.83
     thousands
    0.82
     Jeremiah
    0.79
     GALL
    0.76
     tank
    0.75
    Thousands
    0.75
     thousand
    0.73
    mela
    0.73
    Act Density 0.016%

    No Known Activations