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

    Neuronpedia

    INDEX
    Explanations

    Code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'A
    -0.07
    qb
    -0.06
     IsValid
    -0.06
    こんな
    -0.06
     traced
    -0.06
     damned
    -0.06
    รร
    -0.06
    Kenn
    -0.05
     xor
    -0.05
     hubby
    -0.05
    POSITIVE LOGITS
    ?↵↵
    0.08
    /csv
    0.07
    aos
    0.07
     dopl
    0.06
    opening
    0.06
    ")
↵
    0.06
     ).↵
    0.06
    。。↵↵
    0.06
     contestant
    0.06
    ,↵↵
    0.06
    Act Density 0.001%

    No Known Activations