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

    Neuronpedia

    INDEX
    Explanations

    code keywords and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NES
    1.07
    elleen
    1.03
    QU
    1.03
    Mutability
    1.02
    नाइट
    1.00
    BI
    1.00
    Accuracy
    0.98
    Ethnic
    0.98
    GOT
    0.96
    BY
    0.96
    POSITIVE LOGITS
    !\!\
    1.19
     هناخد
    1.10
    +}
    1.09
    \!\
    1.08
     permettant
    1.07
     Chambre
    1.05
    !!!!!!!!!!!!!!!!
    1.05
     rigid
    1.05
     మంది
    1.04
     lamps
    1.04
    Act Density 0.002%

    No Known Activations