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

    Neuronpedia

    INDEX
    Explanations

    words following `allows`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    azz
    0.50
    schule
    0.50
    면
    0.47
    li
    0.46
    tai
    0.46
    Plugin
    0.44
    oon
    0.44
    Plugins
    0.44
    提
    0.43
    ere
    0.43
    POSITIVE LOGITS
     مبس
    0.52
     custodians
    0.51
    χής
    0.49
    ม่า
    0.48
    ਿਤ
    0.47
     dexterity
    0.47
    飴
    0.46
     Lennon
    0.46
     concurs
    0.46
     Coke
    0.45
    Act Density 0.001%

    No Known Activations