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

    Neuronpedia

    INDEX
    Explanations

    quantity and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Wol
    0.48
    Gym
    0.47
    Ao
    0.45
     Gym
    0.45
    โร
    0.44
    ate
    0.44
    Ass
    0.43
    ات
    0.42
    C
    0.42
    S
    0.42
    POSITIVE LOGITS
     destacan
    0.51
     poudre
    0.49
     teinture
    0.49
     manchas
    0.47
     vf
    0.47
     particles
    0.46
     moléculas
    0.46
     explotación
    0.46
     кара
    0.45
     quantités
    0.45
    Act Density 0.004%

    No Known Activations