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

    Neuronpedia

    INDEX
    Explanations

    first-generation students, bootstrapped

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    its
    0.47
    O
    0.46
    Sub
    0.44
    Sen
    0.43
    فيد
    0.43
    Search
    0.42
    ro
    0.42
     sub
    0.41
    TE
    0.40
    RO
    0.40
    POSITIVE LOGITS
     পা
    0.46
     magnétique
    0.46
    aliśmy
    0.44
    mäßig
    0.43
     रिट
    0.43
     произо
    0.43
    hubung
    0.42
    mapStateToProps
    0.41
     энер
    0.41
     ನಾನು
    0.41
    Act Density 0.003%

    No Known Activations