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

    Neuronpedia

    INDEX
    Explanations

    will not or will strive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在
    0.20
    و
    0.19
     fă
    0.17
     генерал
    0.17
     أو
    0.17
     axioms
    0.16
     في
    0.16
    <unused2222>
    0.16
    ي
    0.16
    بان
    0.16
    POSITIVE LOGITS
     gladly
    0.20
     therefore
    0.17
     not
    0.16
     also
    0.16
     the
    0.16
     continue
    0.16
    ot
    0.15
     sure
    0.15
     happily
    0.15
     ensure
    0.14
    Act Density 0.536%

    No Known Activations