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

    Neuronpedia

    INDEX
    Explanations

    compost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *
↵
    -0.06
     Также
    -0.06
    uParam
    -0.06
     friendships
    -0.06
     COLORS
    -0.06
     Sofa
    -0.06
     yı
    -0.06
    -0.06
     नक
    -0.06
     січ
    -0.05
    POSITIVE LOGITS
    cloak
    0.08
     recognizing
    0.07
     Rune
    0.07
     đột
    0.07
     Publish
    0.06
     Declarations
    0.06
    issued
    0.06
    generated
    0.06
    Managing
    0.06
     democratic
    0.06
    Act Density 0.000%

    No Known Activations