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

    Neuronpedia

    INDEX
    Explanations

    Moses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    thal
    -0.08
     bands
    -0.06
    思考
    -0.06
    _TI
    -0.06
     toda
    -0.06
    .Concurrent
    -0.06
     heavy
    -0.06
     cess
    -0.06
    からは
    -0.06
     chưa
    -0.06
    POSITIVE LOGITS
    wrapper
    0.07
    ایط
    0.07
     EventArgs
    0.06
    opens
    0.06
     Zimmer
    0.06
     Magazine
    0.06
     DeepCopy
    0.06
    vision
    0.06
     relev
    0.06
     Produced
    0.06
    Act Density 0.014%

    No Known Activations