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

    Neuronpedia

    INDEX
    Explanations

    conversation structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Schra
    1.08
     TPR
    1.06
     (%)
    1.03
     CPM
    0.95
    ksh
    0.89
     strlen
    0.89
    Shr
    0.89
    ghar
    0.89
    Ram
    0.88
     starch
    0.87
    POSITIVE LOGITS
    nikom
    1.10
    ництво
    1.05
     botella
    1.02
    await
    0.98
     Marietta
    0.98
     Piedmont
    0.98
     Asheville
    0.97
    Bloc
    0.95
    隔離
    0.93
     async
    0.93
    Act Density 0.375%

    No Known Activations