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

    Neuronpedia

    INDEX
    Explanations

    ITS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     скры
    -0.07
     anus
    -0.06
     NRL
    -0.06
     Basis
    -0.06
     TIFF
    -0.06
    uxtap
    -0.06
    あり
    -0.06
    Sibling
    -0.06
     Angebot
    -0.06
     SU
    -0.06
    POSITIVE LOGITS
    \)
    0.07
    \">
    0.07
    олод
    0.07
    ันก
    0.07
    CompatActivity
    0.07
     Portland
    0.07
     Appears
    0.07
    ()){
    0.06
    oplan
    0.06
    426
    0.06
    Act Density 0.001%

    No Known Activations