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

    Neuronpedia

    INDEX
    Explanations

    squeeze action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stints
    0.66
     толькі
    0.65
    胱
    0.63
    یثیت
    0.61
     doing
    0.57
     crook
    0.56
    ensibly
    0.55
    Dang
    0.55
    менно
    0.55
     materially
    0.54
    POSITIVE LOGITS
    м
    0.72
     indica
    0.56
     esquina
    0.56
     Stimmung
    0.55
     claro
    0.54
    amos
    0.53
    amiento
    0.53
    ı
    0.53
    мм
    0.52
     раствора
    0.52
    Act Density 0.050%

    No Known Activations