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

    Neuronpedia

    INDEX
    Explanations

    book titles and subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rometer
    0.35
    ्रेंस
    0.33
    urken
    0.32
     બની
    0.32
    meshgrid
    0.32
    مسه
    0.32
     gripper
    0.31
    梫
    0.31
    जीर
    0.30
    clinton
    0.30
    POSITIVE LOGITS
    ili
    0.32
    𝘺
    0.29
     Eli
    0.29
    tai
    0.29
     nM
    0.29
    tect
    0.28
     μεγαλ
    0.28
    Щ
    0.28
      
    0.28
     Му
    0.28
    Act Density 0.027%

    No Known Activations