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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    だって
    -0.06
    화를
    -0.06
     lone
    -0.06
     brainstorm
    -0.06
    _clause
    -0.06
    Saudi
    -0.06
    conditions
    -0.06
    alink
    -0.06
     referencia
    -0.06
    世
    -0.06
    POSITIVE LOGITS
     trailed
    0.07
     입니다
    0.06
     ©
    0.06
     pellets
    0.06
     imperfect
    0.06
    Jets
    0.06
     '''↵↵
    0.06
     Late
    0.06
     negot
    0.06
    овали
    0.06
    Act Density 0.072%

    No Known Activations