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

    Neuronpedia

    INDEX
    Explanations

    Single letters/abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     소리
    -0.07
    Chance
    -0.07
    ox
    -0.07
    โช
    -0.06
    GameData
    -0.06
    ざ
    -0.06
    =("
    -0.06
    sb
    -0.06
    _warning
    -0.06
     Animal
    -0.06
    POSITIVE LOGITS
     expérience
    0.07
     мик
    0.07
     أفضل
    0.06
    (directory
    0.06
     _,
    0.06
     stojí
    0.06
     �
    0.06
    针
    0.06
    iegel
    0.06
    amam
    0.06
    Act Density 0.015%

    No Known Activations