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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sinful
    -0.07
     midnight
    -0.06
    Subview
    -0.06
     müm
    -0.06
    ifen
    -0.06
     Indicates
    -0.06
    .dataset
    -0.06
    سمبر
    -0.06
    _stride
    -0.06
     أجل
    -0.06
    POSITIVE LOGITS
     секрет
    0.08
     Spe
    0.08
    ी।↵
    0.06
     Gren
    0.06
    ha
    0.06
    HO
    0.06
    娱乐
    0.06
    osen
    0.06
    ouples
    0.06
    Nonce
    0.06
    Act Density 0.016%

    No Known Activations