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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    锣
    -0.08
     slightest
    -0.07
     Imam
    -0.07
     adel
    -0.07
    ﺁ
    -0.07
    malıdır
    -0.06
     isr
    -0.06
    对应
    -0.06
    am
    -0.06
    .Throw
    -0.06
    POSITIVE LOGITS
     décision
    0.08
    	buffer
    0.08
    NP
    0.07
     cookie
    0.07
    ("***
    0.07
     cheaper
    0.07
     Robbie
    0.07
     quận
    0.07
     Rookie
    0.07
     sản
    0.06
    Act Density 0.045%

    No Known Activations