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

    Neuronpedia

    INDEX
    Explanations

    science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [f
    -0.06
    鼓
    -0.06
    _DEAD
    -0.06
     reass
    -0.06
     antibiotic
    -0.06
     sarc
    -0.05
    commit
    -0.05
     bunları
    -0.05
    _ACC
    -0.05
     jury
    -0.05
    POSITIVE LOGITS
    wil
    0.07
    -products
    0.07
    /)
    0.07
     giorno
    0.06
    Boolean
    0.06
    card
    0.06
    DCALL
    0.06
    468
    0.06
     tế
    0.06
     lub
    0.06
    Act Density 0.163%

    No Known Activations