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

    Neuronpedia

    INDEX
    Explanations

    limitations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ingen
    -0.07
     gmail
    -0.06
    .destroyAllWindows
    -0.06
    ]=]
    -0.06
     Gü
    -0.06
     조교
    -0.06
     assail
    -0.06
     Peach
    -0.06
     certif
    -0.06
     Serv
    -0.06
    POSITIVE LOGITS
    ешь
    0.07
    İZ
    0.07
    lady
    0.07
    -shadow
    0.07
    مع
    0.07
    ΙΟΥ
    0.07
    643
    0.06
    /TT
    0.06
    PE
    0.06
    ço
    0.06
    Act Density 0.001%

    No Known Activations