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

    Neuronpedia

    INDEX
    Explanations

    until

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     took
    -0.07
     związku
    -0.07
    嗾
    -0.07
    trad
    -0.07
    ге
    -0.07
    方圆
    -0.07
    larımız
    -0.06
    isNaN
    -0.06
     faults
    -0.06
    趱
    -0.06
    POSITIVE LOGITS
    =DB
    0.08
    崿
    0.07
    Ί
    0.07
    水晶
    0.07
    _SPACE
    0.07
    押金
    0.07
    תבר
    0.07
    用了
    0.07
    成品
    0.07
    𝐌
    0.06
    Act Density 0.016%

    No Known Activations