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

    Neuronpedia

    INDEX
    Explanations

    danger or negativity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compass
    -0.07
    irector
    -0.06
    istrat
    -0.06
    exchange
    -0.06
     anni
    -0.06
    履
    -0.06
    (#
    -0.06
    Stamp
    -0.06
     участие
    -0.06
    CELER
    -0.06
    POSITIVE LOGITS
    ikhail
    0.07
     sharedApplication
    0.07
    _virtual
    0.06
     후보
    0.06
    implified
    0.06
    默认
    0.06
     سبک
    0.06
    číta
    0.06
    δει
    0.06
     retros
    0.06
    Act Density 0.003%

    No Known Activations