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

    Neuronpedia

    INDEX
    Explanations

    self insert reincarnated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.34
    '
    0.32
    :”
    0.27
    Doctors
    0.25
    Ра
    0.24
    Princ
    0.24
    Members
    0.23
    зви
    0.23
     армии
    0.23
    “…
    0.23
    POSITIVE LOGITS
    on
    0.46
     with
    0.46
     avec
    0.38
    at
    0.38
    as
    0.38
     dengan
    0.37
    u
    0.37
     has
    0.36
     với
    0.35
    ين
    0.34
    Act Density 0.000%

    No Known Activations