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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     godt
    -0.08
    発
    -0.07
    .Tools
    -0.07
    Instantiate
    -0.07
    .readAs
    -0.07
    527
    -0.07
    hled
    -0.07
     rainbow
    -0.07
     кожного
    -0.07
    anteed
    -0.06
    POSITIVE LOGITS
    -SA
    0.06
    ;j
    0.06
    YES
    0.06
    IVATE
    0.06
     collector
    0.06
    ZZ
    0.06
     harbor
    0.06
    ุธ
    0.06
     EA
    0.06
     Hulu
    0.05
    Act Density 0.013%

    No Known Activations