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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __':
    -0.59
    :]:
    -0.51
     CWE
    -0.51
    __":
    -0.49
     characteristic
    -0.49
     signatures
    -0.49
    }")]
    -0.49
     vertrou
    -0.47
     noqa
    -0.47
    ("")]
    -0.46
    POSITIVE LOGITS
    AxisAlignment
    0.59
     the
    0.55
     nuages
    0.55
    Jereo
    0.54
     sánh
    0.50
    щення
    0.50
     ostavi
    0.49
     having
    0.48
    achal
    0.47
    picasso
    0.47
    Act Density 0.000%

    No Known Activations