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

    Neuronpedia

    INDEX
    Explanations

    lists of words and phrases following specific starts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     webhook
    0.93
    приклад
    0.89
     waveguides
    0.89
    评标
    0.86
    webhook
    0.84
     rigidbody
    0.84
    rophages
    0.83
    thorace
    0.83
     pdelay
    0.82
     resultlist
    0.81
    POSITIVE LOGITS
    D
    1.19
    E
    1.13
    M
    1.12
    G
    1.07
    L
    1.06
     M
    1.05
     L
    1.05
    T
    1.05
    K
    1.03
    N
    1.02
    Act Density 0.115%

    No Known Activations