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

    Neuronpedia

    INDEX
    Explanations

    local entities and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Latinoamérica
    0.65
     relacion
    0.62
     Übersetzung
    0.61
     potvr
    0.60
    สุดท้าย
    0.60
    龌
    0.59
     Comunic
    0.59
     Doğ
    0.59
     ሃ
    0.59
     Sanger
    0.57
    POSITIVE LOGITS
    t
    0.79
    c
    0.71
    AREA
    0.64
    j
    0.61
    ار
    0.60
    favor
    0.57
    a
    0.55
    AC
    0.54
    ULTY
    0.54
    ch
    0.52
    Act Density 0.007%

    No Known Activations