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

    Neuronpedia

    INDEX
    Explanations

    Numbers and measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    casting
    -0.06
    府
    -0.06
     اصول
    -0.06
    umb
    -0.06
     přech
    -0.06
     многих
    -0.06
    افه
    -0.06
    ascade
    -0.06
    makt
    -0.06
     podporu
    -0.06
    POSITIVE LOGITS
     microwave
    0.07
    Vent
    0.07
     Anton
    0.07
     esse
    0.07
    imageView
    0.06
     Who
    0.06
    (model
    0.06
     Mathematic
    0.06
    іш
    0.06
    (w
    0.06
    Act Density 0.063%

    No Known Activations