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

    Neuronpedia

    INDEX
    Explanations

    names and words from various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    စိတ်အပိုင်း
    0.25
     Kanban
    0.24
     Elektrokhimiya
    0.22
     symbi
    0.22
     Metaverse
    0.22
     Aktion
    0.22
     consensual
    0.21
     Figma
    0.21
     Mandalorian
    0.21
     eSIM
    0.21
    POSITIVE LOGITS
    ↵
    0.29
    u
    0.27
    is
    0.26
    i
    0.25
    -
    0.25
    j
    0.23
    the
    0.23
    е
    0.23
    R
    0.23
    U
    0.23
    Act Density 0.039%

    No Known Activations