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

    Neuronpedia

    INDEX
    Explanations

    common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hatır
    -0.07
     �
    -0.07
    320
    -0.06
     "/");↵
    -0.06
    戸
    -0.06
    644
    -0.06
    onen
    -0.06
    iton
    -0.06
    ıza
    -0.06
    _hand
    -0.06
    POSITIVE LOGITS
     підприєм
    0.07
     certains
    0.07
     ammunition
    0.06
    .LOC
    0.06
     RESULTS
    0.06
    олнитель
    0.06
     التج
    0.06
     organizers
    0.06
     раст
    0.06
     residuals
    0.06
    Act Density 0.000%

    No Known Activations