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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ISO
    -0.09
     exhilarating
    -0.08
     mantra
    -0.08
     Ibiza
    -0.08
     humans
    -0.08
     envis
    -0.08
    瞬
    -0.08
     latent
    -0.07
     ngx
    -0.07
     reinvent
    -0.07
    POSITIVE LOGITS
     Confederate
    0.14
     కాంగ్రెస్
    0.10
     الحرب
    0.09
    (Tree
    0.09
     counties
    0.09
     कांग्रेस
    0.09
     Republican
    0.09
    (Row
    0.09
     impeachment
    0.08
    ennessee
    0.08
    Act Density 0.026%

    No Known Activations