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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curr
    -0.08
     Blick
    -0.08
    -first
    -0.08
     оч
    -0.07
    ነ
    -0.07
    ﺄ
    -0.07
    أستاذ
    -0.07
    艺
    -0.07
     Solver
    -0.07
     אמנם
    -0.07
    POSITIVE LOGITS
    tridge
    0.08
    [w
    0.08
    }s
    0.07
     impatient
    0.07
     knitting
    0.07
    gráf
    0.07
    小狗
    0.06
    בסיס
    0.06
     Sexe
    0.06
    (rx
    0.06
    Act Density 0.004%

    No Known Activations