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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    consumer
    -0.07
    Patterns
    -0.06
    '},
    -0.06
     provoke
    -0.06
    ве
    -0.06
     Brigham
    -0.06
    Trust
    -0.06
     równ
    -0.05
     válido
    -0.05
    ænd
    -0.05
    POSITIVE LOGITS
     overpower
    0.07
     distant
    0.07
    _VER
    0.06
    聚
    0.06
     cerr
    0.06
     Ey
    0.06
     allocating
    0.06
    _att
    0.06
    	ft
    0.06
    regunta
    0.06
    Act Density 0.006%

    No Known Activations