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

    Neuronpedia

    INDEX
    Explanations

    alpha

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Zoo
    -0.08
    icrous
    -0.07
     zoo
    -0.06
    OVER
    -0.06
     �
    -0.06
     historian
    -0.06
    ‌ترین
    -0.06
    기관
    -0.06
    Appearance
    -0.06
    网络
    -0.06
    POSITIVE LOGITS
     Signs
    0.08
     pochop
    0.07
     unser
    0.07
    (term
    0.07
     Kle
    0.06
    rait
    0.06
     Meta
    0.06
     signifies
    0.06
    _pan
    0.06
    isks
    0.06
    Act Density 0.027%

    No Known Activations