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

    Neuronpedia

    INDEX
    Explanations

    constitute

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    聽
    -0.07
     Trần
    -0.07
     světě
    -0.06
     leaking
    -0.06
    	s
    -0.06
     produtos
    -0.06
     mücadele
    -0.06
    BASEPATH
    -0.06
    时候
    -0.06
    _permalink
    -0.06
    POSITIVE LOGITS
     доп
    0.07
     Floral
    0.06
     housed
    0.06
    _configs
    0.06
     constituted
    0.06
     impr
    0.06
     overhead
    0.06
     Aboriginal
    0.06
    ertz
    0.06
    dition
    0.06
    Act Density 0.027%

    No Known Activations