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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zero
    -1.17
     Zero
    -1.02
     zeroes
    -0.89
     ZERO
    -0.88
     zeros
    -0.87
     maximum
    -0.82
    zero
    -0.82
     Maximum
    -0.79
    Zero
    -0.78
    ations
    -0.78
    POSITIVE LOGITS
    ed
    0.74
    ized
    0.60
    ever
    0.56
     anello
    0.51
    etta
    0.50
     florales
    0.50
    e
    0.50
    ist
    0.49
    emia
    0.49
     considerazione
    0.48
    Act Density 0.079%

    No Known Activations