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

    Neuronpedia

    INDEX
    Explanations

    ale

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brigade
    -0.07
     dokonce
    -0.07
    exp
    -0.06
     Как
    -0.06
     decreased
    -0.06
    Howard
    -0.06
    άκ
    -0.06
     Reader
    -0.06
    engo
    -0.06
    [M
    -0.06
    POSITIVE LOGITS
     flesh
    0.07
     Grain
    0.07
     зер
    0.06
    �
    0.06
     contexts
    0.06
     mainAxisAlignment
    0.06
    _RANK
    0.06
     �
    0.06
    ný
    0.06
     فس
    0.06
    Act Density 0.001%

    No Known Activations