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

    Neuronpedia

    INDEX
    Explanations

    drawing lines and repeating sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     categorías
    0.48
     bonnes
    0.47
     bede
    0.46
    ته
    0.46
     metodología
    0.46
     concaten
    0.46
    الم
    0.45
    역
    0.45
    ୋ
    0.45
     creditor
    0.44
    POSITIVE LOGITS
     stories
    0.45
     STORIES
    0.43
     Cycling
    0.42
     MAX
    0.42
     Stories
    0.41
     MAXIMUM
    0.41
     Leth
    0.41
     Maximal
    0.41
     Robotics
    0.40
     Locking
    0.39
    Act Density 0.000%

    No Known Activations