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

    Neuronpedia

    INDEX
    Explanations

    Pronouns referring to people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Collect
    -0.07
    เสน
    -0.06
    13
    -0.06
    ثمان
    -0.06
    .Code
    -0.06
    ücret
    -0.06
    택
    -0.06
     :↵↵
    -0.06
     Benefit
    -0.05
     Collect
    -0.05
    POSITIVE LOGITS
    (frame
    0.07
    jax
    0.06
    (il
    0.06
    summer
    0.06
    .term
    0.06
     Aydın
    0.06
     Messiah
    0.06
    میل
    0.06
    UNG
    0.06
     hashing
    0.06
    Act Density 0.049%

    No Known Activations