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

    Neuronpedia

    INDEX
    Explanations

    notice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isoner
    -0.07
    ppo
    -0.06
     :.
    -0.06
    nda
    -0.06
    discussion
    -0.06
     Evidence
    -0.06
     VS
    -0.06
     modulation
    -0.06
    егодня
    -0.06
     mathematics
    -0.06
    POSITIVE LOGITS
     unaware
    0.07
     insignificant
    0.07
     перев
    0.07
    LOOK
    0.07
    ่อย
    0.07
     waypoint
    0.07
     ř
    0.06
     eins
    0.06
     dirig
    0.06
    .fire
    0.06
    Act Density 0.012%

    No Known Activations