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

    Neuronpedia

    INDEX
    Explanations

    illuminati

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Blocking
    -0.07
     milano
    -0.06
     Sadd
    -0.06
    .Line
    -0.06
    raries
    -0.06
    Styled
    -0.06
     Rue
    -0.06
    .Html
    -0.06
    ')}}">↵
    -0.06
    _tunnel
    -0.05
    POSITIVE LOGITS
    ียวก
    0.07
    jc
    0.07
     глаз
    0.07
     гер
    0.07
    OOD
    0.07
     ^{°}
    0.06
    どう
    0.06
     Flash
    0.06
    sorry
    0.06
     JD
    0.06
    Act Density 0.015%

    No Known Activations