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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bam
    -0.07
    汉
    -0.07
    .getRandom
    -0.06
     festive
    -0.06
     trim
    -0.06
     peux
    -0.06
     获取
    -0.06
     Пред
    -0.06
    ازم
    -0.06
     Clock
    -0.06
    POSITIVE LOGITS
    IR
    0.07
    ,#
    0.06
    IPS
    0.06
     :+:
    0.06
    ;'↵
    0.06
     FAR
    0.06
    趣
    0.06
     memnun
    0.06
    R
    0.06
    tur
    0.06
    Act Density 0.000%

    No Known Activations