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

    Neuronpedia

    INDEX
    Explanations

    codes or identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    बिलिटी
    0.27
     tumorigen
    0.26
     gacche
    0.25
     renversement
    0.25
    疳
    0.25
     sanguí
    0.25
    ἵ
    0.25
    胙
    0.25
    ynaptic
    0.25
     экскур
    0.24
    POSITIVE LOGITS
    0
    0.36
    /
    0.34
    1
    0.33
    +
    0.33
    5
    0.29
    -
    0.28
    3
    0.28
    4
    0.28
    7
    0.28
    well
    0.27
    Act Density 0.218%

    No Known Activations