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

    Neuronpedia

    INDEX
    Explanations

    Random text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [parent
    -0.07
     περί
    -0.06
     Cristina
    -0.06
     unas
    -0.06
     lassen
    -0.06
    Drink
    -0.06
    έν
    -0.06
    му
    -0.06
    ā
    -0.06
    φυ
    -0.06
    POSITIVE LOGITS
     employment
    0.08
    employment
    0.07
     chiến
    0.07
     candidates
    0.07
    rotate
    0.07
     système
    0.06
     shooter
    0.06
    .tolist
    0.06
    Dismiss
    0.06
     Ae
    0.06
    Act Density 0.000%

    No Known Activations