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

    Neuronpedia

    INDEX
    Explanations

    H

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alpin
    0.39
     स्पेस
    0.38
     ALPINE
    0.38
     spé
    0.38
    riers
    0.37
     remboursement
    0.37
    陘
    0.36
    ibilité
    0.36
     alp
    0.35
     தெரிவித்தனர்
    0.35
    POSITIVE LOGITS
     bienn
    0.39
    subsec
    0.38
    Subgraph
    0.37
    acyjnych
    0.36
     doubles
    0.35
     verdes
    0.35
     Dias
    0.35
    getDouble
    0.35
    柽
    0.35
    тира
    0.34
    Act Density 0.000%

    No Known Activations