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

    Neuronpedia

    INDEX
    Explanations

    are/which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inal
    -0.07
    inally
    -0.07
     Updates
    -0.07
    ident
    -0.07
    owane
    -0.07
    сть
    -0.07
    owl
    -0.07
    qui
    -0.06
    ?!
    -0.06
    ongyang
    -0.06
    POSITIVE LOGITS
    |`↵
    0.08
    .erase
    0.07
     jazy
    0.07
     )↵↵↵
    0.07
    _bridge
    0.07
     بیمه
    0.07
    (EIF
    0.06
     thieves
    0.06
     dataGridView
    0.06
    )this
    0.06
    Act Density 0.060%

    No Known Activations