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

    Neuronpedia

    INDEX
    Explanations

    mean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    โซ
    -0.07
    anon
    -0.07
     cris
    -0.07
    ᵀ
    -0.07
    JA
    -0.07
     "*.
    -0.06
     �
    -0.06
     Hd
    -0.06
     cancelButtonTitle
    -0.06
    ("(
    -0.06
    POSITIVE LOGITS
     receptor
    0.08
    水稻
    0.07
     Swedish
    0.07
     debacle
    0.07
    igion
    0.07
    attering
    0.07
     décembre
    0.07
     destroyer
    0.07
     Giants
    0.07
    ividad
    0.07
    Act Density 0.003%

    No Known Activations