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

    Neuronpedia

    INDEX
    Explanations

    code, warnings, and examples

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ##↵↵
    -0.07
     android
    -0.07
    悼
    -0.07
    小型
    -0.07
    bob
    -0.06
    必将
    -0.06
    android
    -0.06
    台北
    -0.06
    可分为
    -0.06
    DEVICE
    -0.06
    POSITIVE LOGITS
    Ḻ
    0.07
    珵
    0.07
    _SETTING
    0.07
    _ST
    0.07
    STANCE
    0.06
    _quiz
    0.06
    SZ
    0.06
     raise
    0.06
     SHE
    0.06
    /activity
    0.06
    Act Density 0.186%

    No Known Activations