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

    Neuronpedia

    INDEX
    Explanations

    pointers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -thread
    -0.07
     cocktails
    -0.07
     body
    -0.06
     CALLBACK
    -0.06
     awkward
    -0.06
    atik
    -0.06
     simulate
    -0.06
     rd
    -0.06
     ni
    -0.06
    -----↵↵
    -0.06
    POSITIVE LOGITS
    _guest
    0.07
     distributes
    0.06
     affirmative
    0.06
     소개
    0.06
     bü
    0.06
    looking
    0.06
    ror
    0.06
     haystack
    0.06
    さ
    0.06
     Kurdish
    0.06
    Act Density 0.008%

    No Known Activations