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

    Neuronpedia

    INDEX
    Explanations

    problems/issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    archivo
    -0.07
     æ
    -0.07
     alors
    -0.07
    _one
    -0.07
    /functions
    -0.07
     Fr
    -0.07
    rss
    -0.06
    App
    -0.06
     hành
    -0.06
    (X
    -0.06
    POSITIVE LOGITS
    .offer
    0.08
    ราะ
    0.08
    вшис
    0.07
     shred
    0.07
    	unset
    0.07
    楂
    0.07
    散热
    0.06
    综艺节目
    0.06
    .lifecycle
    0.06
    lew
    0.06
    Act Density 0.071%

    No Known Activations