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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exponential
    -0.06
     MessageType
    -0.06
     recursively
    -0.06
    StringUtils
    -0.06
     edi
    -0.06
     values
    -0.06
    -0.06
    Excellent
    -0.06
    ูด
    -0.06
    Current
    -0.06
    POSITIVE LOGITS
     komb
    0.07
     σχ
    0.07
    каз
    0.06
     desc
    0.06
     Coron
    0.06
     mistaken
    0.06
    Paused
    0.06
     corrupted
    0.06
     вниз
    0.06
     xs
    0.06
    Act Density 0.019%

    No Known Activations