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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     variability
    -0.07
     smoother
    -0.06
    ---↵↵
    -0.06
     اض
    -0.06
    十三
    -0.06
    side
    -0.06
    無しさん
    -0.06
    :");
↵
    -0.06
     stubborn
    -0.06
     "{$
    -0.06
    POSITIVE LOGITS
     Engel
    0.06
     hangs
    0.06
     direkt
    0.06
    يدة
    0.06
    _PRIVATE
    0.06
     rotate
    0.06
     trusts
    0.06
     Races
    0.06
    unds
    0.06
     Hanson
    0.06
    Act Density 0.027%

    No Known Activations