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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     $\
    -0.07
    xBB
    -0.07
    }=
    -0.07
    ī
    -0.07
    .Connect
    -0.07
    Recent
    -0.06
    ]]=
    -0.06
    Practice
    -0.06
    ??
    -0.06
     kì
    -0.06
    POSITIVE LOGITS
    344
    0.07
    050
    0.06
    _layout
    0.06
    0.06
    �
    0.06
     محمد
    0.06
     parliament
    0.06
    uly
    0.06
    视频
    0.06
     человека
    0.06
    Act Density 0.005%

    No Known Activations