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

    Neuronpedia

    INDEX
    Explanations

    path join dirname

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yeni
    0.86
     nye
    0.82
     Sisters
    0.81
    ρ
    0.81
     Baru
    0.80
     сім
    0.80
     sisters
    0.79
    ních
    0.79
     Folgen
    0.78
     τα
    0.78
    POSITIVE LOGITS
    সই
    0.77
     concede
    0.76
     בת
    0.72
    ócz
    0.71
    となっている
    0.70
    slidesPerView
    0.69
     ComVisible
    0.69
     עי
    0.68
    defn
    0.68
    に含ま
    0.67
    Act Density 0.001%

    No Known Activations