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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.49
    as
    0.46
     obstructions
    0.45
    AS
    0.45
    ಂಚ
    0.44
    ids
    0.43
    G
    0.43
    ap
    0.43
    S
    0.43
    Makes
    0.42
    POSITIVE LOGITS
     Lupin
    0.51
     Alpine
    0.45
     Jakarta
    0.44
     Karak
    0.44
     Pentium
    0.44
     caranya
    0.44
     Gayatri
    0.43
    länd
    0.43
     Karab
    0.43
     Spaghetti
    0.43
    Act Density 0.008%

    No Known Activations