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

    Neuronpedia

    INDEX
    Explanations

    arguments and debates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .And
    -0.08
    Nach
    -0.07
     Katherine
    -0.06
    adies
    -0.06
    caret
    -0.06
    iná
    -0.06
     tongues
    -0.06
    iề
    -0.06
    religious
    -0.06
    Friendly
    -0.06
    POSITIVE LOGITS
    (rb
    0.07
     xyz
    0.06
     игра
    0.06
    igraphy
    0.06
    调整
    0.06
    رفة
    0.06
     xls
    0.06
    δε
    0.06
     "---
    0.06
     lexical
    0.06
    Act Density 0.000%

    No Known Activations