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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     debated
    -0.08
    อาช
    -0.06
     о
    -0.06
     greed
    -0.06
    Eb
    -0.06
     lan
    -0.06
     внимание
    -0.06
    @Transactional
    -0.06
    bir
    -0.05
     QUAL
    -0.05
    POSITIVE LOGITS
    Working
    0.07
    '](
    0.06
     ups
    0.06
    reatment
    0.06
    �
    0.06
    _FILES
    0.06
     anything
    0.06
     servi
    0.06
     Check
    0.06
    �
    0.06
    Act Density 0.000%

    No Known Activations