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

    Neuronpedia

    INDEX
    Explanations

    superlatives and positives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Expo
    -0.07
    ilen
    -0.07
     Bristol
    -0.07
     cds
    -0.06
    _ten
    -0.06
    774
    -0.06
     Brew
    -0.06
    ophile
    -0.06
    icensed
    -0.06
     눈
    -0.06
    POSITIVE LOGITS
    SRC
    0.06
    	best
    0.06
    _bias
    0.06
    电话
    0.06
    _Settings
    0.06
    _SRC
    0.06
    YSIS
    0.06
    FLAG
    0.06
    ertificate
    0.06
    елеф
    0.06
    Act Density 0.124%

    No Known Activations