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

    Neuronpedia

    INDEX
    Explanations

    rotation or spinning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Marche
    0.83
    㧔
    0.76
    ，《
    0.75
    herlands
    0.71
     Жен
    0.71
    জনক
    0.70
    🌂
    0.69
    gangen
    0.68
     Wanita
    0.68
    రించి
    0.66
    POSITIVE LOGITS
     anode
    0.75
     secondaire
    0.71
     eccess
    0.70
     aislado
    0.70
    adiator
    0.70
     correto
    0.69
     आयोजित
    0.69
     shielding
    0.68
     gyroscope
    0.68
    ar
    0.67
    Act Density 0.000%

    No Known Activations