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

    Neuronpedia

    INDEX
    Explanations

    Property descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     활
    -0.07
    煎
    -0.07
    gst
    -0.07
     enthusiastically
    -0.07
    _bot
    -0.07
     initiating
    -0.07
    ことがあります
    -0.07
    国内外
    -0.06
     alum
    -0.06
     Unknown
    -0.06
    POSITIVE LOGITS
    	HAL
    0.08
    _RO
    0.08
    应急预案
    0.08
     Legendary
    0.07
    แค
    0.07
    جزاء
    0.07
    -average
    0.07
    exampleInput
    0.07
     ];
    0.07
    *',
    0.07
    Act Density 0.051%

    No Known Activations