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

    Neuronpedia

    INDEX
    Explanations

    opposing groups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ventional
    -0.08
    _PIPELINE
    -0.07
    ağın
    -0.07
     meme
    -0.06
     persuaded
    -0.06
    �
    -0.06
    -agent
    -0.06
    -msg
    -0.06
    mist
    -0.06
     Studi
    -0.06
    POSITIVE LOGITS
     Principal
    0.07
    OBJ
    0.06
     Πρό
    0.06
    erior
    0.06
     Việt
    0.06
     西
    0.06
     吉
    0.06
     potential
    0.06
     urlencode
    0.06
     contradict
    0.06
    Act Density 0.058%

    No Known Activations