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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alc
    -0.32
    rita
    -0.32
     virgin
    -0.27
    ï½Ģ
    -0.27
    hil
    -0.26
     Territories
    -0.26
    è¿ĻäºĽ
    -0.25
    oment
    -0.25
     wor
    -0.25
     podium
    -0.25
    POSITIVE LOGITS
    建议
    0.25
    logan
    0.25
    -effect
    0.25
    -effects
    0.24
    /null
    0.24
    /dis
    0.24
    MOST
    0.24
     componentWill
    0.24
    .Slf
    0.24
    [U
    0.23
    Act Density 0.275%

    No Known Activations