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

    Neuronpedia

    INDEX
    Explanations

    to be or to pay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    voli
    0.44
     dosy
    0.42
    inent
    0.41
    rieron
    0.39
     appending
    0.39
    aziz
    0.39
     pouring
    0.38
    zeko
    0.38
    oczy
    0.38
    нологи
    0.38
    POSITIVE LOGITS
     scad
    0.39
    凭
    0.37
     ਰਾ
    0.36
     شئ
    0.35
    佾
    0.35
    Creo
    0.34
     Pigeon
    0.34
     Restaurant
    0.34
     pigeon
    0.33
    ュー
    0.33
    Act Density 0.000%

    No Known Activations