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

    Neuronpedia

    INDEX
    Explanations

    colons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    date
    -0.08
    兕
    -0.07
    ߜ
    -0.07
     Dove
    -0.07
     ו
    -0.07
    .readline
    -0.07
     sich
    -0.07
    -Cds
    -0.06
     fa
    -0.06
    	ft
    -0.06
    POSITIVE LOGITS
     unreasonable
    0.08
    entric
    0.07
     Monetary
    0.07
    раб
    0.07
    냉
    0.07
    mixed
    0.07
    밧
    0.07
    Ren
    0.06
    testimonial
    0.06
    쨉
    0.06
    Act Density 0.001%

    No Known Activations