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

    Neuronpedia

    INDEX
    Explanations

    coding scripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	x
    -0.07
     Obesity
    -0.07
     retrieving
    -0.07
     рядом
    -0.06
    んだ
    -0.06
    ,nil
    -0.06
    さんは
    -0.06
     totalmente
    -0.06
     ister
    -0.06
    الت
    -0.06
    POSITIVE LOGITS
     �
    0.07
    คล
    0.06
    .Automation
    0.06
    .ByteString
    0.06
    (kind
    0.06
     �
    0.06
     géné
    0.06
     developments
    0.06
    _guid
    0.06
    -book
    0.06
    Act Density 0.016%

    No Known Activations