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

    Neuronpedia

    INDEX
    Explanations

    direction, movement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \uff
    -0.08
    こんな
    -0.07
     SqlParameter
    -0.07
     shameful
    -0.07
    highest
    -0.07
    (prog
    -0.07
    ota
    -0.07
    培训
    -0.06
    Sigma
    -0.06
     "."
    -0.06
    POSITIVE LOGITS
     preço
    0.06
     Mat
    0.06
     serge
    0.06
    eksiyon
    0.06
     phosphory
    0.06
    broken
    0.06
    Iteration
    0.06
     Hearth
    0.06
    ایر
    0.05
     España
    0.05
    Act Density 0.244%

    No Known Activations