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

    Neuronpedia

    INDEX
    Explanations

    action verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DataTable
    -0.06
    /<
    -0.06
    (inflater
    -0.06
     when
    -0.06
     chặt
    -0.06
     jsou
    -0.06
     Tư
    -0.06
    .byId
    -0.06
    .application
    -0.06
    (factory
    -0.06
    POSITIVE LOGITS
     Syrian
    0.07
    لا
    0.07
    "All
    0.06
     transformers
    0.06
    578
    0.06
     Patel
    0.06
    ught
    0.06
    ною
    0.06
    interactive
    0.06
     vanished
    0.06
    Act Density 0.032%

    No Known Activations