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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Julio
    -0.07
     Reed
    -0.06
    intelligence
    -0.06
     where
    -0.06
     incorporates
    -0.06
     Buccane
    -0.06
     Bien
    -0.06
    America
    -0.06
     traveling
    -0.06
    	ti
    -0.06
    POSITIVE LOGITS
     Eq
    0.06
    驱
    0.06
    _GRAPH
    0.06
    _ast
    0.06
    筋
    0.06
    краї
    0.06
    リカ
    0.06
    maal
    0.06
    άρχ
    0.06
    (stdout
    0.06
    Act Density 0.003%

    No Known Activations