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

    Neuronpedia

    INDEX
    Explanations

    code with parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অর্চনা
    0.41
    っていう
    0.40
    ਨ
    0.38
    Precio
    0.38
    Returned
    0.38
    媜
    0.38
     nörd
    0.38
     റേ
    0.38
     अर्चना
    0.37
    आईसी
    0.37
    POSITIVE LOGITS
    ognito
    0.37
    ried
    0.37
    ద్
    0.36
     Santiago
    0.35
     mines
    0.35
     essi
    0.35
     regenerative
    0.34
    形
    0.34
    දහ
    0.33
    iers
    0.33
    Act Density 0.018%

    No Known Activations