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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -core
    -0.07
     WikiLeaks
    -0.06
    iative
    -0.06
     obedient
    -0.06
     Options
    -0.06
     traditionally
    -0.06
    zeros
    -0.06
     study
    -0.06
     Coverage
    -0.06
    族
    -0.06
    POSITIVE LOGITS
    を持
    0.06
     fasta
    0.06
     Honolulu
    0.06
    _feed
    0.06
     shorten
    0.06
    yectos
    0.06
    asını
    0.06
    ยอด
    0.06
     Diff
    0.06
    )^
    0.06
    Act Density 0.190%

    No Known Activations