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

    Neuronpedia

    INDEX
    Explanations

    affiliation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    progressive
    0.38
     Schoen
    0.37
    ளிடம்
    0.36
     hånd
    0.36
     Handmade
    0.35
     zones
    0.35
    浲
    0.35
     collectible
    0.34
    जोन
    0.34
     discrete
    0.34
    POSITIVE LOGITS
     affiliation
    2.14
    affiliation
    1.91
     affiliations
    1.88
     affili
    1.58
     affiliated
    1.56
     afili
    1.48
    affiliated
    1.34
     affiliate
    1.25
     affiliates
    1.18
     afiliados
    1.13
    Act Density 0.005%

    No Known Activations