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

    Neuronpedia

    INDEX
    Explanations

    computer science techniques

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alleged
    -0.07
     interrupts
    -0.06
    Cum
    -0.06
    imestone
    -0.06
    [Boolean
    -0.06
     міс
    -0.06
    عی
    -0.06
     laugh
    -0.06
     luxurious
    -0.06
    _$
    -0.06
    POSITIVE LOGITS
     },{↵
    0.07
    ]=(
    0.06
    �
    0.06
     ern
    0.06
     ------------------------------------------------------------------------------------------------
    0.06
     '">'
    0.06
    940
    0.06
     初
    0.06
     procedure
    0.06
     Trinity
    0.06
    Act Density 0.029%

    No Known Activations