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

    Neuronpedia

    INDEX
    Explanations

    code snippets/URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Uno
    -0.08
    ṳ
    -0.07
    lık
    -0.07
     Tec
    -0.07
    مناقشة
    -0.07
    涛
    -0.07
    	Collection
    -0.07
    azeera
    -0.07
    毅
    -0.07
    ﮎ
    -0.07
    POSITIVE LOGITS
     SY
    0.08
     thing
    0.07
     betting
    0.07
     kle
    0.07
     cookie
    0.07
    oracle
    0.07
    /K
    0.07
     DY
    0.07
    .Client
    0.07
    �
    0.06
    Act Density 0.020%

    No Known Activations