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

    Neuronpedia

    INDEX
    Explanations

    Software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thấp
    -0.06
    ونی
    -0.06
    ('.');↵
    -0.06
     начале
    -0.06
     shade
    -0.06
    .getSession
    -0.06
     här
    -0.06
    ’m
    -0.06
     sagte
    -0.06
     сделать
    -0.06
    POSITIVE LOGITS
    astered
    0.07
    리그
    0.07
     hôn
    0.07
    첨부
    0.06
     Шев
    0.06
    ording
    0.06
    aybe
    0.06
    Verification
    0.06
    (other
    0.06
     Diagnostic
    0.06
    Act Density 0.000%

    No Known Activations