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

    Neuronpedia

    INDEX
    Explanations

    ensive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     climbers
    -0.07
    ait
    -0.07
     Lover
    -0.07
     just
    -0.07
     Calculator
    -0.07
     Rewards
    -0.06
    (alpha
    -0.06
     McCain
    -0.06
     scared
    -0.06
     recruits
    -0.06
    POSITIVE LOGITS
     extensive
    0.11
     Tmax
    0.08
     extensively
    0.08
    _kses
    0.07
    DeviceInfo
    0.07
    سي
    0.07
    eways
    0.07
    moth
    0.07
    SSI
    0.07
    exter
    0.07
    Act Density 0.009%

    No Known Activations