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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yapım
    -0.06
    ствует
    -0.06
     stereo
    -0.06
     yağ
    -0.06
     Overrides
    -0.06
     disdain
    -0.06
    选择
    -0.06
     buen
    -0.06
    ivre
    -0.06
    豆
    -0.06
    POSITIVE LOGITS
    _sizes
    0.07
     foremost
    0.07
     @{$
    0.06
     pardon
    0.06
     Alo
    0.06
    rove
    0.06
     fadeIn
    0.06
    0.06
    viously
    0.06
    _correction
    0.06
    Act Density 0.260%

    No Known Activations