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

    Neuronpedia

    INDEX
    Explanations

    `START` scene markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ascertained
    0.41
    ముఖ
    0.41
     SBOM
    0.41
    䒿
    0.40
     phúc
    0.39
    oMatrix
    0.39
    etano
    0.38
    abhavam
    0.38
    தேச
    0.38
    𝐾
    0.38
    POSITIVE LOGITS
    '...
    0.42
    ...'
    0.39
    '=
    0.39
    ​,
    0.38
    ►
    0.37
    TC
    0.36
    ​
    0.36
     '}
    0.36
    '/>
    0.36
    */}
    0.35
    Act Density 0.000%

    No Known Activations