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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ITED
    -0.08
    _soup
    -0.07
    기는
    -0.07
    計劃
    -0.06
    .article
    -0.06
     včetně
    -0.06
    cum
    -0.06
    Steam
    -0.06
    ANCES
    -0.06
    _cloud
    -0.06
    POSITIVE LOGITS
     for
    0.08
     hg
    0.07
     haf
    0.07
    homme
    0.07
     /\
    0.06
    for
    0.06
    CDF
    0.06
    scr
    0.06
    'S
    0.06
     para
    0.06
    Act Density 0.059%

    No Known Activations