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

    Neuronpedia

    INDEX
    Explanations

    fitting and adding items

    np_acts-logits-general · gemini-2.5-flash-lite

    insert or add

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    0.90
    ING
    0.75
    4
    0.73
    3
    0.71
    لي
    0.70
    2
    0.70
    ;
    0.69
    ৩৩
    0.68
     noastră
    0.67
     što
    0.64
    POSITIVE LOGITS
    ل
    1.13
    is
    0.98
    il
    0.92
    on
    0.92
     It
    0.89
    ल
    0.89
    л
    0.87
    م
    0.84
    et
    0.79
    ur
    0.79
    Act Density 1.441%

    No Known Activations