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

    Neuronpedia

    INDEX
    Explanations

    nut variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     निभा
    0.41
     Vikings
    0.39
    ogue
    0.38
    Mood
    0.36
    Illuminate
    0.36
    睒
    0.36
     импе
    0.35
    ized
    0.35
    Stub
    0.35
    Mind
    0.34
    POSITIVE LOGITS
     nut
    0.79
     Nut
    0.77
    Nut
    0.71
    cracker
    0.69
     NUT
    0.67
     nutri
    0.66
    NUT
    0.65
    nut
    0.65
    ritional
    0.64
     nutr
    0.58
    Act Density 0.004%

    No Known Activations