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

    Neuronpedia

    INDEX
    Explanations

    Random excerpts from documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ghan
    -0.07
    "]
    -0.06
    Countries
    -0.06
    Whenever
    -0.06
    .GenerationType
    -0.06
    Steel
    -0.06
    common
    -0.06
    	loop
    -0.06
    Dam
    -0.06
     मण
    -0.06
    POSITIVE LOGITS
    INY
    0.07
    �
    0.06
     Λα
    0.06
    low
    0.06
     waypoints
    0.06
    lew
    0.06
     pains
    0.06
    _Ex
    0.06
    ypes
    0.06
     наб
    0.06
    Act Density 0.001%

    No Known Activations