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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sudah
    -0.08
     bath
    -0.06
    _nth
    -0.06
     Into
    -0.06
    UserData
    -0.06
     Fel
    -0.06
    参
    -0.06
     суб
    -0.06
    Trad
    -0.06
    ukkit
    -0.06
    POSITIVE LOGITS
     tắt
    0.07
    積
    0.07
    خر
    0.07
     круг
    0.06
    _duplicates
    0.06
    酸
    0.06
     Memor
    0.06
    _usage
    0.06
     substantially
    0.06
     dile
    0.06
    Act Density 0.014%

    No Known Activations