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

    Neuronpedia

    INDEX
    Explanations

    /internal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     likelihood
    -0.07
     tend
    -0.07
     deadly
    -0.06
     containers
    -0.06
    .sim
    -0.06
     classifiers
    -0.06
     analyzer
    -0.06
    _QU
    -0.06
    _USART
    -0.06
     barbecue
    -0.06
    POSITIVE LOGITS
    /internal
    0.08
    SECTION
    0.07
    (Equal
    0.07
    .ps
    0.07
     linestyle
    0.06
    們
    0.06
     ApplicationException
    0.06
    ẫ
    0.06
     harvest
    0.06
    unce
    0.06
    Act Density 0.001%

    No Known Activations