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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ety
    -0.07
    markup
    -0.06
    instagram
    -0.06
    Hospital
    -0.06
     gr
    -0.06
     tem
    -0.06
    PRESENT
    -0.06
    olicit
    -0.06
    anean
    -0.06
     betray
    -0.06
    POSITIVE LOGITS
     unexpectedly
    0.07
    >\
    0.06
     interception
    0.06
     henüz
    0.06
     vọng
    0.06
     itu
    0.06
    超过
    0.06
    (kwargs
    0.06
     علاق
    0.06
    RP
    0.06
    Act Density 0.000%

    No Known Activations