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

    Neuronpedia

    INDEX
    Explanations

    titles starting with "The"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    の種類
    0.61
     maladies
    0.55
     sanctions
    0.54
    ])
    0.54
    的总
    0.52
     nationalities
    0.49
    、
    0.49
    。”
    0.49
     deletions
    0.48
     demarcation
    0.48
    POSITIVE LOGITS
    ب
    0.64
    خ
    0.63
    ان
    0.63
    ه
    0.62
    in
    0.61
    an
    0.61
    ay
    0.61
    k
    0.61
    es
    0.55
    il
    0.55
    Act Density 0.036%

    No Known Activations