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

    Neuronpedia

    INDEX
    Explanations

    moths and twitter followers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     salad
    -0.08
     Salad
    -0.08
     મ
    -0.08
    <uint
    -0.07
     প্রক
    -0.07
     Mir
    -0.07
    announcement
    -0.07
    ndag
    -0.07
    ULO
    -0.07
    nergy
    -0.07
    POSITIVE LOGITS
     несколь
    0.10
     kilka
    0.08
    ("---
    0.08
     компания
    0.08
     birkaç
    0.07
     "---
    0.07
     companies
    0.07
    ERN
    0.07
    sev
    0.07
    شركة
    0.07
    Act Density 0.000%

    No Known Activations