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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exp
    -0.07
     अर
    -0.07
    .Navigator
    -0.07
     ********************************
    -0.06
     dues
    -0.06
    usic
    -0.06
    -mail
    -0.06
    /stream
    -0.06
     Mare
    -0.06
    ilingual
    -0.06
    POSITIVE LOGITS
    [axis
    0.06
    <len
    0.06
     {↵↵↵↵
    0.06
    _EST
    0.06
     Premier
    0.06
    0.06
    (days
    0.06
     At
    0.05
     Wrest
    0.05
    :void
    0.05
    Act Density 0.123%

    No Known Activations