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

    Neuronpedia

    INDEX
    Explanations

    forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _↵↵
    -0.07
    ).↵↵↵
    -0.07
     ..↵↵
    -0.07
    ,tp
    -0.07
    ).↵↵
    -0.07
    .setVisible
    -0.07
    كترو
    -0.07
    ມ
    -0.07
    =message
    -0.07
    砆
    -0.07
    POSITIVE LOGITS
     אנחנו
    0.07
     hobbies
    0.07
    三百
    0.07
    攻坚战
    0.07
     amigos
    0.07
    riet
    0.07
     Secret
    0.07
    殴
    0.07
    农
    0.07
     números
    0.07
    Act Density 0.103%

    No Known Activations