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

    Neuronpedia

    INDEX
    Explanations

    words ending in suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chatbots
    0.51
     Jupyter
    0.51
     chatbot
    0.48
     GDPR
    0.48
     ChatGPT
    0.47
     softmax
    0.47
     interoper
    0.45
     ARIMA
    0.45
     Oculus
    0.44
     AutoML
    0.44
    POSITIVE LOGITS
    ianSpace
    0.39
    tyard
    0.38
    achment
    0.38
    ishment
    0.37
    forcement
    0.36
    itory
    0.36
    ెంట్
    0.35
    ון
    0.35
    modation
    0.34
    ordinary
    0.34
    Act Density 1.050%

    No Known Activations