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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    circ
    -0.07
     дум
    -0.07
     Answers
    -0.07
     Listening
    -0.06
    entlich
    -0.06
     claro
    -0.06
     briefing
    -0.06
    -go
    -0.06
     casualty
    -0.06
    Ease
    -0.06
    POSITIVE LOGITS
    нула
    0.07
    اساس
    0.07
    arhus
    0.06
     rootReducer
    0.06
    haus
    0.06
    ักก
    0.06
    811
    0.06
     Franco
    0.06
    .assertRaises
    0.06
     trag
    0.06
    Act Density 0.000%

    No Known Activations