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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     چهار
    -0.07
     sectarian
    -0.06
    _rectangle
    -0.06
    yl
    -0.06
    地區
    -0.06
    교회
    -0.06
    LEVEL
    -0.06
     drinking
    -0.06
    离开
    -0.06
    eggies
    -0.06
    POSITIVE LOGITS
     mal
    0.07
    rtle
    0.07
     Alma
    0.07
    (dy
    0.07
    ...
↵
    0.07
     frags
    0.06
    _ZONE
    0.06
    onation
    0.06
    _seg
    0.06
    prene
    0.06
    Act Density 0.025%

    No Known Activations