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

    Neuronpedia

    INDEX
    Explanations

    equations with variables and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ach
    0.77
    am
    0.75
    ayakan
    0.72
    íonn
    0.71
    fänger
    0.71
    ittä
    0.71
    il
    0.70
    ab
    0.70
    ată
    0.70
    adă
    0.70
    POSITIVE LOGITS
    니
    0.73
    して
    0.70
     а
    0.69
    ক
    0.68
    ף
    0.67
    𝚃
    0.66
     a
    0.65
    ر
    0.64
     т
    0.62
     যাবতীয়
    0.62
    Act Density 0.000%

    No Known Activations