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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     overcoming
    -0.07
     OUTER
    -0.07
     шк
    -0.07
     sep
    -0.07
     bride
    -0.06
     Schedule
    -0.06
     Xxx
    -0.06
     altre
    -0.06
     Lanka
    -0.06
     rollout
    -0.06
    POSITIVE LOGITS
     кня
    0.07
    .contents
    0.06
    い
    0.06
    NSNotificationCenter
    0.06
    جد
    0.06
    -tests
    0.06
     αυ
    0.06
     successors
    0.06
    oti
    0.06
     necklace
    0.06
    Act Density 0.001%

    No Known Activations