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

    Neuronpedia

    INDEX
    Explanations

    time durations in hours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilta
    0.88
    Mind
    0.82
    τας
    0.80
    い
    0.79
    羊
    0.77
    sir
    0.77
    筍
    0.76
    stein
    0.74
    牛
    0.73
    രുന്ന
    0.73
    POSITIVE LOGITS
     hapl
    0.93
    واحد
    0.80
    遵循
    0.79
     dehydrogenase
    0.78
     surrog
    0.78
     tante
    0.76
    ائف
    0.75
     indire
    0.75
     داخ
    0.75
    indazol
    0.75
    Act Density 0.127%

    No Known Activations