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

    Neuronpedia

    INDEX
    Explanations

    nature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Discussion
    -0.08
    容易
    -0.07
     Glad
    -0.07
     Fernando
    -0.07
    permanent
    -0.07
     soll
    -0.06
     ($("#
    -0.06
     Elm
    -0.06
     Ensemble
    -0.06
    lish
    -0.06
    POSITIVE LOGITS
     nature
    0.15
     Nature
    0.15
    nature
    0.14
    Nature
    0.12
    ATURE
    0.08
     Natur
    0.07
    au
    0.07
    .
↵
    0.07
     affili
    0.06
     thu
    0.06
    Act Density 0.009%

    No Known Activations