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

    Neuronpedia

    INDEX
    Explanations

    relation comma name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    0.88
    ق
    0.77
    न
    0.75
    ки
    0.68
    লে
    0.67
    ن
    0.66
    на
    0.65
    is
    0.64
    то
    0.64
    ри
    0.63
    POSITIVE LOGITS
    0.78
     Padres
    0.54
     Lagrangian
    0.49
     thermostat
    0.49
     ();
    0.49
     of
    0.48
     revolver
    0.48
     precursor
    0.47
     定
    0.47
     Boolean
    0.46
    Act Density 0.004%

    No Known Activations