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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elapsed
    -0.07
    archives
    -0.07
    [K
    -0.07
     IReadOnly
    -0.06
    	bs
    -0.06
    _uc
    -0.06
    BigInt
    -0.06
    	fs
    -0.06
    (R
    -0.06
     judged
    -0.06
    POSITIVE LOGITS
    険
    0.07
    reib
    0.06
    …the
    0.06
    music
    0.06
    -.
    0.06
     офици
    0.06
    sur
    0.06
    ')){↵
    0.06
    }
↵
↵
↵
↵
    0.06
    ligne
    0.06
    Act Density 0.091%

    No Known Activations