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

    Neuronpedia

    INDEX
    Explanations

    uniquely followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    -3.39
    </strong>
    -3.16
    </h3>
    -2.44
    _{
    -2.41
    </u>
    -2.36
    趼
    -2.33
    -2.31
     トラベル
    -2.22
    ⽌
    -2.22
    </sub>
    -2.20
    POSITIVE LOGITS
    *
    2.75
    re
    2.64
    ly
    2.50
    in
    2.44
    [
    2.41
    Some
    2.28
     sorta
    2.28
    庒
    2.25
    ’
    2.20
    —
    2.20
    Act Density 0.005%

    No Known Activations