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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _JSON
    -0.07
     dav
    -0.07
    _disk
    -0.07
     kapı
    -0.07
    _hours
    -0.07
    _placeholder
    -0.06
     kem
    -0.06
     лік
    -0.06
     Lok
    -0.06
     relocated
    -0.06
    POSITIVE LOGITS
     �
    0.06
    徽
    0.06
    quartered
    0.06
    Enums
    0.06
    _mB
    0.06
    .EN
    0.05
    wart
    0.05
    ();}↵
    0.05
    '][]
    0.05
    ansom
    0.05
    Act Density 0.099%

    No Known Activations