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

    Neuronpedia

    INDEX
    Explanations

    abstraction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Impl
    -0.07
    _CHAN
    -0.07
    而导致
    -0.06
    ,line
    -0.06
     �
    -0.06
     Capability
    -0.06
    努
    -0.06
    芒
    -0.06
    minus
    -0.06
    芴
    -0.06
    POSITIVE LOGITS
     ADS
    0.07
    emm
    0.07
    드립니다
    0.07
     moeten
    0.07
     contractor
    0.07
    ujący
    0.07
    烻
    0.07
     цены
    0.07
     Powered
    0.07
     trained
    0.06
    Act Density 0.004%

    No Known Activations