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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exempt
    -0.07
     sisters
    -0.06
    Safe
    -0.06
     तहत
    -0.06
    ecure
    -0.06
    егодня
    -0.06
    '].'/
    -0.06
    Try
    -0.06
    _connect
    -0.06
    níci
    -0.06
    POSITIVE LOGITS
    察
    0.06
    .*?)
    0.06
     tud
    0.06
    olf
    0.06
    181
    0.06
    �
    0.06
    :[[
    0.06
    isLoggedIn
    0.06
     }));↵
    0.06
     nebezpeč
    0.06
    Act Density 0.051%

    No Known Activations