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

    Neuronpedia

    INDEX
    Explanations

    names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     più
    0.61
     tärke
    0.61
     beeinfl
    0.56
     mitä
    0.54
     поддержка
    0.54
     как
    0.54
    ಚ್
    0.54
    Ｒ
    0.54
     seperti
    0.53
     öst
    0.53
    POSITIVE LOGITS
     robbers
    0.62
     majest
    0.53
     handsome
    0.48
     robberies
    0.48
     bandits
    0.47
     carelessly
    0.47
     waiters
    0.46
     cheques
    0.46
     arrog
    0.46
     mutton
    0.46
    Act Density 0.001%

    No Known Activations