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

    Neuronpedia

    INDEX
    Explanations

    .Dec

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝓉
    -0.07
    🥖
    -0.07
     checkout
    -0.06
     Merkel
    -0.06
     COURT
    -0.06
    遽
    -0.06
     MUCH
    -0.06
    ROT
    -0.06
    .BLACK
    -0.06
    ichage
    -0.06
    POSITIVE LOGITS
     themes
    0.07
    设计器
    0.07
    素材
    0.07
    甸
    0.06
    },{"
    0.06
    记得
    0.06
    ':"
    0.06
    сал
    0.06
    澎湃
    0.06
    永利
    0.06
    Act Density 0.002%

    No Known Activations