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

    Neuronpedia

    INDEX
    Explanations

    resolution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Logic
    -0.07
    )));
↵
    -0.07
    버전
    -0.07
     بازیگر
    -0.06
    .cr
    -0.06
     згод
    -0.06
     stares
    -0.06
     Locator
    -0.06
     bullshit
    -0.06
     confort
    -0.06
    POSITIVE LOGITS
    ovich
    0.07
     Tuy
    0.07
     Geh
    0.06
     utan
    0.06
    にか
    0.06
     있고
    0.06
     ges
    0.06
     θ
    0.06
     thấp
    0.06
     unfortunately
    0.06
    Act Density 0.030%

    No Known Activations