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

    Neuronpedia

    INDEX
    Explanations

    users

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GORITHM
    -0.07
     Antwort
    -0.06
     рождения
    -0.06
     arrogant
    -0.06
    °E
    -0.06
    ори
    -0.06
    _proc
    -0.06
     Warfare
    -0.06
     spilled
    -0.06
    ën
    -0.06
    POSITIVE LOGITS
     jurisdictions
    0.08
    ฒ
    0.06
     navigator
    0.06
     giy
    0.06
     elim
    0.06
    ()
    0.06
     <
    0.06
    ług
    0.06
    nave
    0.06
     cf
    0.06
    Act Density 0.025%

    No Known Activations