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

    Neuronpedia

    INDEX
    Explanations

    unleash your potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hashes
    0.52
     hoteles
    0.50
     tokamaks
    0.49
    割り
    0.49
     muros
    0.48
     importants
    0.47
     costumes
    0.47
    〔
    0.46
     revistas
    0.46
     Outfitters
    0.46
    POSITIVE LOGITS
     creativity
    0.52
     القدر
    0.50
    powers
    0.46
    the
    0.46
     Creativity
    0.45
    ﺨ
    0.43
    Powers
    0.43
     vocabulary
    0.41
    erede
    0.40
     unleash
    0.40
    Act Density 0.005%

    No Known Activations