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

    Neuronpedia

    INDEX
    Explanations

    a specific number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.40
     boutique
    0.31
     now
    0.31
    ,
    0.30
     city
    0.30
    0.30
     special
    0.29
     sand
    0.29
     play
    0.29
     restaurant
    0.29
    POSITIVE LOGITS
    Pyrazole
    0.39
    Methoxy
    0.37
    􀂃
    0.36
    Imidazole
    0.35
    testAvg
    0.35
    ሢ
    0.35
     Bhagavato
    0.34
    PointerException
    0.34
     Labrenzia
    0.34
    Fragmentation
    0.34
    Act Density 0.000%

    No Known Activations