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

    Neuronpedia

    INDEX
    Explanations

    known

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ro
    -0.08
     scooter
    -0.07
     clinicians
    -0.07
    /or
    -0.06
    βολ
    -0.06
    >+
    -0.06
    fadeIn
    -0.06
    -game
    -0.06
    ,ep
    -0.06
    _activate
    -0.06
    POSITIVE LOGITS
     wisdom
    0.07
    鄉
    0.07
     víde
    0.07
    _elem
    0.06
    agne
    0.06
    EEK
    0.06
     VERIFY
    0.06
     informace
    0.06
    TZ
    0.06
    _TM
    0.06
    Act Density 0.016%

    No Known Activations