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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moons
    -0.08
    ursions
    -0.07
    -rich
    -0.07
     wilderness
    -0.06
     Estimates
    -0.06
     intentionally
    -0.06
    /Index
    -0.06
     على
    -0.06
    ρούν
    -0.06
     Rogers
    -0.06
    POSITIVE LOGITS
     of
    0.10
    of
    0.09
    Of
    0.08
     Of
    0.08
     amore
    0.07
    -of
    0.07
     докум
    0.07
    opa
    0.07
    OF
    0.07
     OF
    0.07
    Act Density 0.167%

    No Known Activations