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

    Neuronpedia

    INDEX
    Explanations

    annual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ляє
    -0.08
     Funk
    -0.08
     pregunta
    -0.07
     somewhere
    -0.07
     안
    -0.07
     clearer
    -0.07
    alog
    -0.07
     naive
    -0.06
     tease
    -0.06
     cock
    -0.06
    POSITIVE LOGITS
     annual
    0.16
     Annual
    0.14
    Annual
    0.12
     annually
    0.10
     ann
    0.08
    annual
    0.08
    _ann
    0.08
    ans
    0.08
    NL
    0.07
    Bins
    0.07
    Act Density 0.006%

    No Known Activations