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

    Neuronpedia

    INDEX
    Explanations

    IPFS or indexing

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bel
    2.66
    bel
    2.27
     Bel
    2.23
    Bel
    2.20
    BEL
    1.72
     BEL
    1.65
     бел
    1.35
     벨
    1.34
    벨
    1.26
     belts
    1.25
    POSITIVE LOGITS
    াযোগ
    0.37
     முக
    0.37
    ories
    0.34
     Bead
    0.34
    ORIES
    0.34
    ﻅ
    0.33
     lod
    0.33
     Imit
    0.33
    kowitz
    0.33
     numberWithFloat
    0.32
    Act Density 0.003%

    No Known Activations