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

    Neuronpedia

    INDEX
    Explanations

    released

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plemented
    -0.07
    Tab
    -0.07
    cos
    -0.06
    -New
    -0.06
     obedience
    -0.06
     key
    -0.06
    ference
    -0.06
    ز
    -0.06
    ti
    -0.06
    TER
    -0.06
    POSITIVE LOGITS
     IQueryable
    0.08
    ardır
    0.08
     ifstream
    0.07
    	UI
    0.07
     initialState
    0.07
    "https
    0.07
     oči
    0.07
     eslint
    0.07
     выгляд
    0.07
     самым
    0.07
    Act Density 0.012%

    No Known Activations