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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    leding
    0.28
    творення
    0.26
    oxylated
    0.26
     Prerequisites
    0.26
    ление
    0.25
    érés
    0.25
    ématique
    0.25
    っている
    0.25
     elicited
    0.25
    ableness
    0.25
    POSITIVE LOGITS
     behem
    0.29
     Alfa
    0.29
     Alpen
    0.28
     Kub
    0.28
     Osaka
    0.28
     Tux
    0.27
     Kyushu
    0.27
     Luxor
    0.27
    Би
    0.27
     ZX
    0.27
    Act Density 0.207%

    No Known Activations