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

    Neuronpedia

    INDEX
    Explanations

    even if, especially the

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

    introducing specific examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ları
    0.68
     kawaida
    0.67
     be
    0.66
     ativa
    0.64
    ق
    0.64
     are
    0.64
    ()=>{
    0.63
     altre
    0.63
     as
    0.61
     ahí
    0.61
    POSITIVE LOGITS
    .
    0.84
    t
    0.71
    ام
    0.66
    ت
    0.59
    esters
    0.55
    तः
    0.53
    ان
    0.53
    -
    0.51
    자가
    0.50
    یی
    0.49
    Act Density 3.839%

    No Known Activations