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

    Neuronpedia

    INDEX
    Explanations

    **Quotation marks, formatting, chorus**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    slam
    0.54
     rode
    0.50
     MND
    0.47
     pobre
    0.47
     halve
    0.47
     Dota
    0.46
     sociaux
    0.46
     Miao
    0.45
     piti
    0.45
     igra
    0.44
    POSITIVE LOGITS
     or
    0.46
    NET
    0.44
    Transit
    0.44
    CustomerID
    0.42
    Palette
    0.41
    련
    0.40
     customer
    0.40
     certificate
    0.40
    oyloxy
    0.39
     certifications
    0.39
    Act Density 0.000%

    No Known Activations