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

    Neuronpedia

    INDEX
    Explanations

    movement and position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     collegamento
    0.52
     ingresso
    0.50
     appropriateness
    0.48
    stärke
    0.48
     indicato
    0.48
    რც
    0.48
     резер
    0.47
    الق
    0.47
    kowania
    0.47
    लिड
    0.47
    POSITIVE LOGITS
     by
    0.87
    literally
    0.70
    โดย
    0.68
     without
    0.65
    On
    0.62
    at
    0.61
     oleh
    0.60
     from
    0.59
    มากมาย
    0.59
    right
    0.58
    Act Density 0.001%

    No Known Activations