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

    Neuronpedia

    INDEX
    Explanations

    variable star

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    azim
    0.52
     Василь
    0.48
    OUIS
    0.47
     Jaw
    0.46
     पैनल
    0.46
    ગાહી
    0.46
     Sunil
    0.45
     Lij
    0.45
    CP
    0.45
    ATIONS
    0.45
    POSITIVE LOGITS
    물이
    0.50
    та
    0.49
    د
    0.49
    های
    0.48
    electrons
    0.48
    iskt
    0.47
    λ
    0.47
    ռ
    0.47
    ନ
    0.47
    था
    0.46
    Act Density 0.000%

    No Known Activations