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

    Neuronpedia

    INDEX
    Explanations

    p-adic numbers and Eric Matthes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     assent
    0.38
     READING
    0.37
    ದ್
    0.37
     inactive
    0.36
     अमन
    0.36
    ТУ
    0.35
    冬天
    0.35
     slab
    0.34
    Reading
    0.34
    Objectives
    0.34
    POSITIVE LOGITS
     الساعه
    0.43
    adee
    0.41
    otic
    0.40
     expiration
    0.39
    trunc
    0.38
    ity
    0.37
    expiration
    0.37
    tic
    0.36
    體的
    0.36
     הזה
    0.36
    Act Density 0.000%

    No Known Activations