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

    Neuronpedia

    INDEX
    Explanations

    OF

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -message
    -0.06
    ило
    -0.06
    Nam
    -0.06
    htt
    -0.06
    éf
    -0.06
    lish
    -0.06
     طریق
    -0.06
    iculo
    -0.06
    tracks
    -0.06
    )-(
    -0.06
    POSITIVE LOGITS
     Portland
    0.07
     ant
    0.07
     kotlin
    0.06
     ViewHolder
    0.06
     Gerald
    0.06
     Horn
    0.06
     discriminate
    0.06
     реп
    0.06
     htt
    0.06
    ignite
    0.06
    Act Density 0.000%

    No Known Activations