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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🛏
    -0.07
    额度
    -0.07
     beta
    -0.07
    حال
    -0.06
    hrs
    -0.06
     ℕ
    -0.06
     Developed
    -0.06
    שדה
    -0.06
    _aligned
    -0.06
     kod
    -0.06
    POSITIVE LOGITS
     Bengals
    0.07
    <char
    0.07
     Interracial
    0.07
     Sgt
    0.07
    版权声明
    0.07
    _short
    0.07
    ())
↵
    0.07
     Goes
    0.07
    animals
    0.07
    ians
    0.07
    Act Density 0.039%

    No Known Activations