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

    Neuronpedia

    INDEX
    Explanations

    .com URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    জনের
    0.84
     kır
    0.72
    -|
    0.69
     TCL
    0.66
    jení
    0.66
    প্রিম
    0.66
     lanza
    0.65
    Fols
    0.65
     ቢ
    0.65
     schlecht
    0.65
    POSITIVE LOGITS
    Defence
    1.07
     Defence
    1.05
     defence
    1.05
    defence
    0.96
    Royal
    0.86
     Royal
    0.80
     Permanent
    0.77
     रॉयल
    0.75
     Quân
    0.73
     Armed
    0.72
    Act Density 0.009%

    No Known Activations