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

    Neuronpedia

    INDEX
    Explanations

    `raise NotImplementedError`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    滉
    0.49
    Memorial
    0.46
     т
    0.46
    κι
    0.46
    bible
    0.45
    treating
    0.43
    Mons
    0.43
    ले
    0.42
     Xuan
    0.42
     Macmillan
    0.42
    POSITIVE LOGITS
    持久
    0.47
    /
    0.44
    ures
    0.43
    os
    0.43
    arda
    0.42
    ure
    0.42
    ocer
    0.41
     mockery
    0.41
    ired
    0.41
    izes
    0.41
    Act Density 0.001%

    No Known Activations