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

    Neuronpedia

    INDEX
    Explanations

    8 or 9

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     authorities
    -0.07
    igidBody
    -0.07
    יכון
    -0.07
    ≂
    -0.07
    illage
    -0.07
    ﯘ
    -0.07
     isVisible
    -0.06
    évolution
    -0.06
     לצאת
    -0.06
    ita
    -0.06
    POSITIVE LOGITS
    Salt
    0.08
    ()==
    0.07
     Causes
    0.07
     Kale
    0.07
     mar
    0.06
    SELL
    0.06
     lowers
    0.06
    Key
    0.06
     Kodi
    0.06
    Metrics
    0.06
    Act Density 0.038%

    No Known Activations