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

    Neuronpedia

    INDEX
    Explanations

    company names followed by services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adverb
    0.36
     confounding
    0.32
    鬏
    0.31
    羡慕
    0.30
     आशा
    0.30
     Göttingen
    0.29
     overfitting
    0.29
     physiologically
    0.29
     scepticism
    0.29
     somew
    0.28
    POSITIVE LOGITS
     T
    0.40
     H
    0.37
    爀
    0.37
     K
    0.36
    free
    0.35
    ビング
    0.35
    AP
    0.34
     E
    0.34
    リ
    0.33
     F
    0.33
    Act Density 0.070%

    No Known Activations