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

    Neuronpedia

    INDEX
    Explanations

    Local vs large

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ล
    -0.08
    柔
    -0.07
    Jer
    -0.06
    yn
    -0.06
     benchmark
    -0.06
     pinpoint
    -0.06
    антаж
    -0.06
     captions
    -0.06
     dabei
    -0.06
     понима
    -0.06
    POSITIVE LOGITS
    ,param
    0.07
    flow
    0.06
    157
    0.06
    _OCC
    0.06
    UU
    0.06
     UObject
    0.06
    Optimizer
    0.06
    Floor
    0.06
    passed
    0.06
     Kosovo
    0.06
    Act Density 0.071%

    No Known Activations