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

    Neuronpedia

    INDEX
    Explanations

    I Love / minimum monthly / common territory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     productColor
    0.41
    魘
    0.40
     makna
    0.38
     HStack
    0.38
     होला
    0.38
    eezy
    0.37
     ["[
    0.36
     victorias
    0.36
     moguće
    0.36
     acabado
    0.35
    POSITIVE LOGITS
     got
    0.41
    beg
    0.40
    got
    0.40
    it
    0.38
    itri
    0.37
    t
    0.36
    l
    0.36
    ках
    0.36
    5
    0.36
    sci
    0.36
    Act Density 0.000%

    No Known Activations