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

    Neuronpedia

    INDEX
    Explanations

    browser

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _NEAR
    -0.07
    .“↵↵
    -0.07
     vä
    -0.06
    54
    -0.06
    _MODE
    -0.06
    13
    -0.06
     irritated
    -0.06
    113
    -0.06
     skill
    -0.06
     zaz
    -0.06
    POSITIVE LOGITS
     policymakers
    0.07
     milestones
    0.06
    親
    0.06
    λιά
    0.06
     Investments
    0.06
     fulfilling
    0.06
     sexuales
    0.06
     republik
    0.06
     زیرا
    0.06
    0.06
    Act Density 0.013%

    No Known Activations