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

    Neuronpedia

    INDEX
    Explanations

    compound interest calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    x
    0.55
    k
    0.51
    d
    0.49
    c
    0.46
    ish
    0.43
     is
    0.41
    t
    0.41
     compatible
    0.40
    b
    0.40
     are
    0.39
    POSITIVE LOGITS
     shearing
    0.42
     Nurses
    0.42
    нік
    0.42
     Portraits
    0.42
    गिंग
    0.42
    🏥
    0.41
     tedious
    0.40
     radiologists
    0.40
     नर्स
    0.40
     avviene
    0.40
    Act Density 0.000%

    No Known Activations