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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rehabilitation
    -0.07
     Eden
    -0.06
    ảng
    -0.06
    ativas
    -0.06
    /full
    -0.06
    一瞬间
    -0.06
    ajes
    -0.06
    տ
    -0.06
    /libs
    -0.06
    խ
    -0.06
    POSITIVE LOGITS
     Vad
    0.07
    Upper
    0.07
     wors
    0.07
    elo
    0.07
     highly
    0.07
     Down
    0.07
    марк
    0.07
    )",
    0.07
    gate
    0.07
     increased
    0.07
    Act Density 0.006%

    No Known Activations