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

    Neuronpedia

    INDEX
    Explanations

    available

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    1.92
    ()=>{
    1.64
    어야
    1.59
    ה
    1.57
     oauth
    1.52
    ती
    1.51
    ATION
    1.51
    ERS
    1.51
    기
    1.49
    UD
    1.48
    POSITIVE LOGITS
    az
    1.77
    and
    1.74
    af
    1.70
    ir
    1.68
    ments
    1.67
    ut
    1.66
    um
    1.65
     Въ
    1.62
    ight
    1.61
    pence
    1.55
    Act Density 0.026%

    No Known Activations