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

    Neuronpedia

    INDEX
    Explanations

    replaying/rehearsing events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     relaxed
    -0.07
    ?>
↵
↵
    -0.07
    ціон
    -0.06
    燕
    -0.06
     Yayın
    -0.06
    帕
    -0.06
    iliz
    -0.06
    憶
    -0.06
     underst
    -0.06
    อว
    -0.06
    POSITIVE LOGITS
    udio
    0.06
    程
    0.06
     ngọt
    0.06
    wiki
    0.06
    things
    0.06
     جنسی
    0.06
    金额
    0.06
    /img
    0.06
    nave
    0.06
     GOD
    0.06
    Act Density 0.030%

    No Known Activations