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

    Neuronpedia

    INDEX
    Explanations

    above

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -log
    -0.07
    descending
    -0.07
    .slot
    -0.07
    ity
    -0.06
    �
    -0.06
    Prob
    -0.06
     locality
    -0.06
     Sha
    -0.06
    .sup
    -0.06
    .exit
    -0.06
    POSITIVE LOGITS
     debated
    0.07
     ülke
    0.07
     vier
    0.07
     Pere
    0.06
     pear
    0.06
     mỗi
    0.06
     místo
    0.06
     hết
    0.06
     STILL
    0.06
     pard
    0.06
    Act Density 0.002%

    No Known Activations