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

    Neuronpedia

    INDEX
    Explanations

    module

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nutzen
    -0.07
    <
    -0.06
     června
    -0.06
     hayata
    -0.06
    434
    -0.06
    arefa
    -0.06
    	open
    -0.06
    媒体
    -0.06
    fffffff
    -0.06
     burner
    -0.06
    POSITIVE LOGITS
    ीं।
    0.06
    -author
    0.06
     جامع
    0.06
     musicians
    0.06
    _ELEMENT
    0.06
     Almighty
    0.06
    _bag
    0.06
     Succ
    0.06
     OEM
    0.06
    ται
    0.06
    Act Density 0.004%

    No Known Activations