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

    Neuronpedia

    INDEX
    Explanations

    language constructs and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    דים
    0.44
    Ultimate
    0.44
    Selecting
    0.42
     mengaj
    0.42
     Selecting
    0.41
    Avoiding
    0.41
    re
    0.41
    "
    0.41
    azione
    0.39
    Unity
    0.39
    POSITIVE LOGITS
     කා
    0.47
     hét
    0.45
    ómicos
    0.45
     destaca
    0.44
     climates
    0.43
     sí
    0.43
     ಶ
    0.43
    }]}\
    0.43
     destac
    0.42
     fertilisers
    0.42
    Act Density 0.007%

    No Known Activations