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

    Neuronpedia

    INDEX
    Explanations

    prospect or follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    1.99
    naj
    1.85
    د
    1.82
    نة
    1.80
    mata
    1.79
    tenance
    1.73
    rice
    1.66
    urious
    1.65
    ridden
    1.63
    stoke
    1.57
    POSITIVE LOGITS
    fficial
    3.18
    ֹ
    2.72
    pportun
    2.48
    ppy
    2.48
    othing
    2.48
    ppen
    2.48
    bserv
    2.42
    pportunities
    2.35
    ften
    2.34
    anything
    2.31
    Act Density 0.207%

    No Known Activations