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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exhibit
    -0.07
    ethylene
    -0.07
     yardım
    -0.07
    loating
    -0.06
    ,—
    -0.06
    ,current
    -0.06
     heav
    -0.06
    anical
    -0.06
     cửa
    -0.06
    .cls
    -0.06
    POSITIVE LOGITS
    бит
    0.08
    ليزية
    0.07
     TInt
    0.06
    elerinden
    0.06
     vyk
    0.06
     subur
    0.06
    INESS
    0.06
    얼
    0.06
    Har
    0.06
     года
    0.06
    Act Density 0.007%

    No Known Activations