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

    Neuronpedia

    INDEX
    Explanations

    Punctuation and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    phan
    -0.06
     England
    -0.06
    \Exceptions
    -0.06
     Aure
    -0.06
    rlen
    -0.06
    Union
    -0.06
     Psy
    -0.06
    iece
    -0.06
    jem
    -0.06
     decade
    -0.06
    POSITIVE LOGITS
    直接
    0.07
    pro
    0.06
     ald
    0.06
    -json
    0.06
    iclass
    0.06
     AuthService
    0.06
    	endif
    0.05
    ITIONAL
    0.05
     सफ
    0.05
    "↵↵
    0.05
    Act Density 0.000%

    No Known Activations