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

    Neuronpedia

    INDEX
    Explanations

    demographic statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Baghd
    -0.07
    -with
    -0.06
     Oper
    -0.06
    ffen
    -0.06
     urgency
    -0.06
     erót
    -0.06
     Inspir
    -0.06
    ो।
    -0.06
    으니
    -0.06
     Souls
    -0.06
    POSITIVE LOGITS
    ocomplete
    0.07
     становится
    0.07
    Requires
    0.07
    (recipe
    0.06
    xDC
    0.06
    azar
    0.06
    adapter
    0.06
    503
    0.06
    STRUCTOR
    0.06
    Features
    0.06
    Act Density 0.000%

    No Known Activations