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

    Neuronpedia

    INDEX
    Explanations

    reveals a clue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ين
    0.83
    KNOWN
    0.80
    يه
    0.76
    ों
    0.75
    ק
    0.75
    s
    0.71
    KEL
    0.70
    Be
    0.70
    el
    0.69
    K
    0.69
    POSITIVE LOGITS
     estrogens
    1.09
     esconder
    1.09
     resolver
    1.08
     indicada
    1.05
     coalgebras
    1.04
     mastect
    1.02
     halides
    1.01
     করিয়ে
    1.01
    ificação
    1.00
     neutrophils
    1.00
    Act Density 0.000%

    No Known Activations