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

    Neuronpedia

    INDEX
    Explanations

    story, history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tendr
    -0.08
    뱔
    -0.08
     интер
    -0.07
     IGNORE
    -0.07
     tiers
    -0.07
    溃
    -0.07
     wides
    -0.07
    ğer
    -0.07
     الأورو
    -0.07
    ��이터
    -0.06
    POSITIVE LOGITS
     לעבוד
    0.07
    amu
    0.07
     misconduct
    0.07
    呈現
    0.07
     estava
    0.07
    เขต
    0.07
    准确
    0.07
     Abram
    0.07
    _exists
    0.07
     Explicit
    0.07
    Act Density 0.050%

    No Known Activations