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

    Neuronpedia

    INDEX
    Explanations

    using tunnel construction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zahlen
    0.39
    mao
    0.38
    lipstick
    0.38
    postId
    0.37
    䀨
    0.37
     StringBuffer
    0.37
     पोस्ट
    0.36
     Rutgers
    0.35
     पेंट
    0.35
    śc
    0.35
    POSITIVE LOGITS
     Kathleen
    0.45
     Tina
    0.41
    Tina
    0.41
     machines
    0.41
    Adventure
    0.40
     adventure
    0.39
    Delivery
    0.39
     terv
    0.38
    Machine
    0.38
     geographical
    0.38
    Act Density 0.003%

    No Known Activations