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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ́c
    -0.07
     '-')↵
    -0.06
    legal
    -0.06
     resigned
    -0.06
    oin
    -0.06
    useRal
    -0.06
    dek
    -0.06
     cancers
    -0.06
    ,opt
    -0.06
    ============
    -0.06
    POSITIVE LOGITS
    матрива
    0.07
    @index
    0.07
    	Label
    0.06
     QPushButton
    0.06
    χία
    0.06
    	ID
    0.06
    <Item
    0.06
    льт
    0.06
    (custom
    0.06
     distrib
    0.06
    Act Density 0.043%

    No Known Activations