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

    Neuronpedia

    INDEX
    Explanations

    000

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -inf
    -0.07
     หน
    -0.06
     moms
    -0.06
     yani
    -0.06
    璃
    -0.06
     süt
    -0.06
     output
    -0.06
     tính
    -0.06
     Tud
    -0.06
     insurgents
    -0.06
    POSITIVE LOGITS
     Gor
    0.07
     Essays
    0.06
    ήν
    0.06
     jc
    0.06
     examinations
    0.06
    _ins
    0.06
    apikey
    0.06
    aban
    0.06
     defence
    0.06
    вана
    0.06
    Act Density 0.005%

    No Known Activations