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

    Neuronpedia

    INDEX
    Explanations

    Multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     caval
    -0.07
     stringstream
    -0.07
     prop
    -0.06
     traced
    -0.06
     bulun
    -0.06
    cot
    -0.06
     decade
    -0.06
     vocals
    -0.06
    wen
    -0.06
     zus
    -0.06
    POSITIVE LOGITS
    inerary
    0.07
    ******
↵
    0.07
    코
    0.07
    िह
    0.07
    _memory
    0.06
    orrar
    0.06
    /List
    0.06
     counselor
    0.06
     imageName
    0.06
    Ѓ
    0.06
    Act Density 0.001%

    No Known Activations