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

    Neuronpedia

    INDEX
    Explanations

    future intent and obligation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    える
    0.43
    šit
    0.40
    માં
    0.38
     ధర
    0.36
     fantástico
    0.36
    áš
    0.36
    ामध्ये
    0.35
    뭣
    0.35
     समन्वय
    0.35
    수는
    0.34
    POSITIVE LOGITS
    to
    0.66
     to
    0.65
    t
    0.51
    us
    0.50
    N
    0.49
    ana
    0.45
    in
    0.44
    el
    0.43
     -
    0.43
    inat
    0.43
    Act Density 0.362%

    No Known Activations