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

    Neuronpedia

    INDEX
    Explanations

    specific phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    がいる
    0.52
    телям
    0.50
     olarak
    0.48
     muscular
    0.48
     overloading
    0.48
    லம்
    0.47
     acquaintance
    0.46
    learned
    0.46
     нова
    0.46
     kulland
    0.46
    POSITIVE LOGITS
     Statue
    0.51
     Shrine
    0.46
     Region
    0.46
     Irwin
    0.46
     Resolución
    0.45
    టీఎం
    0.44
     Week
    0.44
     Provo
    0.44
     Guo
    0.43
     Sitio
    0.43
    Act Density 0.000%

    No Known Activations