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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ders
    -0.07
     banda
    -0.07
    Voltage
    -0.07
     tools
    -0.06
    atha
    -0.06
     voxel
    -0.06
     Nob
    -0.06
    八
    -0.06
    อพ
    -0.06
    }`,↵
    -0.06
    POSITIVE LOGITS
     Pek
    0.07
     Warning
    0.07
    경
    0.06
    Bond
    0.06
    ичний
    0.06
    ص
    0.06
     truths
    0.06
     predecess
    0.06
    PyObject
    0.06
    ，请
    0.06
    Act Density 0.000%

    No Known Activations