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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bbw
    -0.06
    .”↵↵
    -0.06
    ."↵↵
    -0.06
    Votre
    -0.06
    :
↵
↵
    -0.06
    苹果
    -0.06
    ])**
    -0.06
    !”↵↵
    -0.06
    Rare
    -0.06
     |
    -0.06
    POSITIVE LOGITS
    \Command
    0.07
    toHaveBeenCalledTimes
    0.07
     Participation
    0.07
    _ft
    0.06
    _RESP
    0.06
     thuê
    0.06
    hooks
    0.06
    _radio
    0.06
     osobní
    0.06
    َر
    0.06
    Act Density 0.368%

    No Known Activations