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

    Neuronpedia

    INDEX
    Explanations

    accusations of wrongdoing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    &)
    -0.06
     speaks
    -0.06
    ilated
    -0.06
     intrig
    -0.06
     cooperate
    -0.06
    琳
    -0.06
    uyện
    -0.06
    اره
    -0.06
    treeview
    -0.06
     Emergency
    -0.05
    POSITIVE LOGITS
     Anchor
    0.07
     uns
    0.07
     втор
    0.07
     optical
    0.07
    _photo
    0.06
     sudoku
    0.06
     SD
    0.06
    _core
    0.06
     micro
    0.06
    ία
    0.06
    Act Density 0.055%

    No Known Activations