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

    Neuronpedia

    INDEX
    Explanations

    multiple

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ysical
    -0.07
    .instance
    -0.07
    Artist
    -0.07
    史上
    -0.07
    (robot
    -0.07
    Convention
    -0.07
    .setTitle
    -0.07
    restaurants
    -0.07
     psyche
    -0.07
    itions
    -0.07
    POSITIVE LOGITS
    热线
    0.08
    .ApplyResources
    0.07
    ]:
↵
    0.07
    居
    0.07
    köp
    0.07
     Hot
    0.07
     -*
    0.07
    _ANDROID
    0.07
    越来越高
    0.06
     bring
    0.06
    Act Density 0.001%

    No Known Activations