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

    Neuronpedia

    INDEX
    Explanations

    numbers and rankings

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

    numbers and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ING
    0.42
    </h2>
    0.42
    ِ
    0.37
     我们
    0.37
    </u>
    0.36
    _
    0.36
    我们
    0.35
     która
    0.35
    -'
    0.35
     बातें
    0.35
    POSITIVE LOGITS
    the
    0.47
    et
    0.46
    d
    0.44
    at
    0.42
    ta
    0.42
    target
    0.39
    b
    0.39
    toned
    0.38
    their
    0.36
    top
    0.36
    Act Density 0.095%

    No Known Activations