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

    Neuronpedia

    INDEX
    Explanations

    parameter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beans
    -0.09
     bean
    -0.08
     invasive
    -0.08
     dones
    -0.08
     actionable
    -0.08
     hacks
    -0.08
    hoven
    -0.08
    .Upload
    -0.07
    ופו
    -0.07
    (done
    -0.07
    POSITIVE LOGITS
     սկզբ
    0.07
     हालांकि
    0.07
    cing
    0.07
     번호
    0.07
    aching
    0.07
     पसंद
    0.07
     Leb
    0.07
     Seg
    0.07
    ILLISECONDS
    0.07
    钟
    0.07
    Act Density 0.004%

    No Known Activations