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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "with"

    np_acts-logits-general · gemini-2.5-flash-lite

    with + descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    0.89
    ara
    0.80
    ak
    0.73
    in
    0.64
     في
    0.64
    ని
    0.63
    써
    0.63
     inactivació
    0.62
    ada
    0.62
     reservados
    0.62
    POSITIVE LOGITS
     with
    1.31
    y
    1.20
    t
    1.03
    ב
    1.00
    ED
    0.94
    ת
    0.93
    l
    0.93
    は
    0.91
    with
    0.89
    WITH
    0.89
    Act Density 0.645%

    No Known Activations