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

    Neuronpedia

    INDEX
    Explanations

    above

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     north
    -0.07
     Nova
    -0.07
     enough
    -0.07
     podob
    -0.06
     infra
    -0.06
    cassert
    -0.06
    itele
    -0.06
    أة
    -0.06
     footprint
    -0.06
    .TestTools
    -0.06
    POSITIVE LOGITS
     Kurd
    0.08
     シ
    0.07
    売
    0.06
     Grad
    0.06
    _ANY
    0.06
    Attributes
    0.06
    ()*
    0.06
    Khi
    0.06
     slim
    0.06
     leveling
    0.06
    Act Density 0.000%

    No Known Activations