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

    Neuronpedia

    INDEX
    Explanations

    positive sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deletion
    -0.07
     Hick
    -0.07
    obic
    -0.06
    "is
    -0.06
     Emergency
    -0.06
     went
    -0.06
     брат
    -0.06
    !
    -0.06
     QGraphics
    -0.06
    γον
    -0.06
    POSITIVE LOGITS
    (setting
    0.07
    Easy
    0.07
    challenge
    0.07
     fick
    0.06
     声
    0.06
    ('/')[-
    0.06
    rists
    0.06
    ’ex
    0.06
    LIBINT
    0.06
     jsou
    0.06
    Act Density 0.048%

    No Known Activations