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

    Neuronpedia

    INDEX
    Explanations

    study inclusion criteria

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ..↵↵
    -0.08
     besides
    -0.08
     multif
    -0.07
    عزي
    -0.07
     OSI
    -0.07
     Casinos
    -0.07
     nhiên
    -0.07
    Billy
    -0.07
     electrical
    -0.07
     חודשים
    -0.07
    POSITIVE LOGITS
    才发现
    0.07
    婆婆
    0.07
    הול
    0.07
    ترك
    0.06
     permission
    0.06
    _freq
    0.06
     buckets
    0.06
    훤
    0.06
    ὡ
    0.06
    comma
    0.06
    Act Density 0.005%

    No Known Activations