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

    Neuronpedia

    INDEX
    Explanations

    questions and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    యా
    0.49
     jawa
    0.48
     अनाउंस
    0.44
     నియ
    0.43
     जमानत
    0.41
     הער
    0.41
    IRCONIUM
    0.41
    igenous
    0.41
     Properties
    0.41
     Ethics
    0.41
    POSITIVE LOGITS
     trên
    0.53
    did
    0.51
    ---’
    0.49
     theo
    0.47
    Databaze
    0.47
     às
    0.46
    elte
    0.45
     caul
    0.44
     soddisf
    0.44
     på
    0.43
    Act Density 0.001%

    No Known Activations