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

    Neuronpedia

    INDEX
    Explanations

    numbers and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BlockFit
    0.34
    LastGen
    0.33
    DanhMucSP
    0.33
    逦
    0.32
    RatingDiff
    0.31
    BlockUsed
    0.31
     zásobníku
    0.31
    𒁾
    0.31
    ോഗ്യ
    0.30
    OutgoingRiver
    0.30
    POSITIVE LOGITS
    0.47
    -
    0.44
    1
    0.44
     and
    0.40
     C
    0.40
    ↵
    0.39
     T
    0.39
    ,
    0.39
     S
    0.39
    4
    0.39
    Act Density 0.135%

    No Known Activations