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

    Neuronpedia

    INDEX
    Explanations

    formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getCQL
    0.24
    📂
    0.23
    reasonably
    0.22
    Substituting
    0.22
    施術
    0.21
    많은
    0.21
    诌
    0.21
    getBlueTeam
    0.21
    apopt
    0.21
    วัสดี
    0.21
    POSITIVE LOGITS
     other
    0.27
     miscellaneous
    0.26
     Other
    0.26
     hybrid
    0.25
     others
    0.25
     Islamic
    0.23
     purely
    0.23
     simple
    0.22
     U
    0.21
     Miscellaneous
    0.21
    Act Density 0.586%

    No Known Activations