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

    Neuronpedia

    INDEX
    Explanations

    New GPT instance context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elesa
    -0.08
     Continental
    -0.08
     Tested
    -0.08
     Psychic
    -0.08
     qarşı
    -0.08
     explored
    -0.08
     Statements
    -0.08
    /car
    -0.08
     leuk
    -0.08
     begleiten
    -0.08
    POSITIVE LOGITS
     afterwards
    0.09
     потом
    0.08
    ోగ
    0.08
     nicer
    0.08
     sauveg
    0.07
     switching
    0.07
     simpler
    0.07
    _switch
    0.07
     FE
    0.07
     backup
    0.07
    Act Density 0.000%

    No Known Activations