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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     собы
    -0.07
     Everest
    -0.06
     Kop
    -0.06
     完
    -0.06
     sting
    -0.06
    otic
    -0.06
     partir
    -0.06
    όμε
    -0.06
    _ng
    -0.06
     Turner
    -0.06
    POSITIVE LOGITS
     ([[
    0.07
     otherwise
    0.07
     hopes
    0.07
    Descriptor
    0.07
     tended
    0.06
     LOVE
    0.06
    -upper
    0.06
     Vũ
    0.06
    absolute
    0.06
    ái
    0.06
    Act Density 0.001%

    No Known Activations