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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ult
    -0.07
     LIC
    -0.06
     beden
    -0.06
     Dems
    -0.06
    ilver
    -0.06
    veloper
    -0.06
    젠
    -0.06
    ्फ
    -0.06
     olup
    -0.06
    victim
    -0.06
    POSITIVE LOGITS
     QVERIFY
    0.06
     أول
    0.06
    .FromSeconds
    0.06
     HIS
    0.06
    _SIGN
    0.06
     zad
    0.06
     Bank
    0.06
    sage
    0.06
    ilit
    0.06
    Structure
    0.06
    Act Density 0.072%

    No Known Activations