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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aerospace
    -0.06
     تعد
    -0.06
     gears
    -0.06
     manslaughter
    -0.06
    339
    -0.06
    .Store
    -0.06
     bothers
    -0.06
    _quota
    -0.06
    _SP
    -0.06
     تیم
    -0.06
    POSITIVE LOGITS
     cork
    0.07
    (DWORD
    0.07
    _subject
    0.07
    .Alignment
    0.07
    ель
    0.07
    ikleri
    0.06
     pož
    0.06
     booty
    0.06
     téměř
    0.06
    proposal
    0.06
    Act Density 0.005%

    No Known Activations