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

    Neuronpedia

    INDEX
    Explanations

    code or technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Georgetown
    -0.07
     Zambia
    -0.07
    木
    -0.06
     지나
    -0.06
     Lena
    -0.06
     кир
    -0.06
    ############
    -0.06
     diver
    -0.06
     указ
    -0.06
     beef
    -0.06
    POSITIVE LOGITS
    Training
    0.06
    ционной
    0.06
     xml
    0.06
     böyle
    0.06
     Giám
    0.06
    probability
    0.06
    Days
    0.06
     Veter
    0.06
     sem
    0.06
    ulse
    0.06
    Act Density 0.000%

    No Known Activations