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

    Neuronpedia

    INDEX
    Explanations

    great combined with other words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    1.17
    il
    1.13
    ри
    1.08
    un
    1.05
    리
    1.03
    व
    1.00
    m
    0.89
    ي
    0.88
    ul
    0.85
    ре
    0.82
    POSITIVE LOGITS
     great
    0.78
    .
    0.77
     GREAT
    0.70
    iva
    0.67
    kova
    0.67
    stion
    0.67
     depository
    0.66
    great
    0.65
    inding
    0.65
     fundament
    0.65
    Act Density 0.016%

    No Known Activations