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

    Neuronpedia

    INDEX
    Explanations

    article excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'int
    -0.07
     iVar
    -0.06
     mín
    -0.06
     إلي
    -0.06
     σε
    -0.06
    larını
    -0.06
    Fold
    -0.06
     nơi
    -0.06
     που
    -0.06
    metis
    -0.06
    POSITIVE LOGITS
    ROWN
    0.07
     respond
    0.07
     clouds
    0.07
     unarmed
    0.06
     closet
    0.06
    _launch
    0.06
    .home
    0.06
     proport
    0.06
    (right
    0.06
    Shoot
    0.06
    Act Density 0.000%

    No Known Activations