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

    Neuronpedia

    INDEX
    Explanations

    y

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zahl
    -0.07
     ecstatic
    -0.06
     ؟
    -0.06
    ()?>
    -0.06
    .INFO
    -0.06
    haf
    -0.06
     accession
    -0.06
    Fonts
    -0.06
     erfahren
    -0.06
    training
    -0.06
    POSITIVE LOGITS
    _experiment
    0.07
     GAS
    0.07
    Politics
    0.07
     plasma
    0.06
     y
    0.06
    Structure
    0.06
     l
    0.06
    ,Y
    0.06
    curity
    0.06
     outlook
    0.06
    Act Density 0.004%

    No Known Activations