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

    Neuronpedia

    INDEX
    Explanations

    conscient

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     horm
    -0.07
     možnost
    -0.07
     Miz
    -0.07
     معنی
    -0.06
    .currentIndex
    -0.06
    �이
    -0.06
     часть
    -0.06
     сім
    -0.06
     chevy
    -0.06
     Devil
    -0.06
    POSITIVE LOGITS
    >`↵
    0.06
    (cat
    0.06
     immedi
    0.06
     monday
    0.06
    -IS
    0.06
    _UINT
    0.06
    �
    0.06
     strongly
    0.06
    >↵
    0.06
    oso
    0.06
    Act Density 0.000%

    No Known Activations