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

    Neuronpedia

    INDEX
    Explanations

    Career interests

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Updater
    -0.07
    (avg
    -0.07
    Avg
    -0.07
     Beer
    -0.06
    Raw
    -0.06
    Staff
    -0.06
    _average
    -0.06
    479
    -0.06
    rtl
    -0.06
     Battery
    -0.06
    POSITIVE LOGITS
    \S
    0.07
    増
    0.06
     Although
    0.06
     patri
    0.06
    Queries
    0.06
     Nä
    0.06
     mosquitoes
    0.06
     ﻣ
    0.06
    مة
    0.06
     З
    0.06
    Act Density 0.011%

    No Known Activations