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
     Kon
    -0.06
     pazar
    -0.06
     seperti
    -0.06
    _km
    -0.06
    Mc
    -0.06
    另一
    -0.06
     Toe
    -0.06
     myList
    -0.06
     surprisingly
    -0.06
    วล
    -0.06
    POSITIVE LOGITS
     triggering
    0.07
     strengthened
    0.07
     rat
    0.07
    LETE
    0.06
     acquired
    0.06
            ↵        ↵        ↵
    0.06
     추천
    0.06
    内
    0.06
    verted
    0.06
    «
    0.06
    Act Density 0.024%

    No Known Activations