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

    Neuronpedia

    INDEX
    Explanations

    frequently

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Conservative
    -0.06
    .Typed
    -0.06
     Ethics
    -0.06
     organizers
    -0.06
     Supports
    -0.06
     ego
    -0.06
     foam
    -0.06
     Shows
    -0.06
     Jose
    -0.06
     admissions
    -0.06
    POSITIVE LOGITS
    `.
    0.07
     PLA
    0.06
    ۱۸
    0.06
     усі
    0.06
    填
    0.06
    .Collapsed
    0.06
    졌다
    0.06
     дал
    0.06
    <br
    0.06
     Lesb
    0.06
    Act Density 0.033%

    No Known Activations