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

    Neuronpedia

    INDEX
    Explanations

    image, code, locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Chi
    0.55
    Leon
    0.54
    OPHY
    0.53
    Natal
    0.51
    Aub
    0.50
    Concerning
    0.50
    RAEL
    0.50
    Germ
    0.50
    uncan
    0.50
    millan
    0.50
    POSITIVE LOGITS
     debounce
    0.66
     ungroup
    0.64
     código
    0.62
     mockup
    0.60
     lashes
    0.60
     tersedia
    0.60
     pelanggan
    0.59
     строк
    0.59
     rigidbody
    0.59
     blocks
    0.58
    Act Density 0.000%

    No Known Activations