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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Scanner
    -0.06
    _cost
    -0.06
     MAX
    -0.06
     Thanksgiving
    -0.06
    _spaces
    -0.06
     evidently
    -0.06
     '/',
    -0.06
     optimization
    -0.06
    _MAX
    -0.06
     Cricket
    -0.06
    POSITIVE LOGITS
    battle
    0.07
    ulous
    0.07
    898
    0.07
     Hera
    0.07
    ucci
    0.06
    هره
    0.06
     Nail
    0.06
    ��
    0.06
     địch
    0.06
     Hilfe
    0.06
    Act Density 0.011%

    No Known Activations