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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rawer
    -0.08
     also
    -0.06
     lety
    -0.06
    Taylor
    -0.06
     rosa
    -0.06
    겼
    -0.06
     Maxwell
    -0.06
     Todd
    -0.06
    PPP
    -0.06
     İngilizce
    -0.06
    POSITIVE LOGITS
     Extr
    0.07
    .del
    0.07
    \$
    0.06
     subjected
    0.06
    _rr
    0.06
     ….
    0.06
     autoc
    0.06
    Inf
    0.06
     automated
    0.06
    販
    0.06
    Act Density 0.017%

    No Known Activations