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

    Neuronpedia

    INDEX
    Explanations

    married

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /problems
    -0.08
    ↖
    -0.08
    INSERT
    -0.07
     ecological
    -0.07
     Hosp
    -0.07
    (initial
    -0.06
     revisit
    -0.06
     recurring
    -0.06
    诗歌
    -0.06
    _CHARSET
    -0.06
    POSITIVE LOGITS
    alsa
    0.08
    ometimes
    0.07
     Manafort
    0.07
    装配
    0.07
    这辈子
    0.07
    .atan
    0.07
    皱纹
    0.07
    农资
    0.07
    Actions
    0.07
    פו
    0.06
    Act Density 0.015%

    No Known Activations