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

    Neuronpedia

    INDEX
    Explanations

    are followed by a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    อ
    1.08
    *
    1.04
    ක්
    1.00
    ist
    0.96
    أن
    0.92
     Newsletter
    0.91
     negativity
    0.91
    -
    0.90
    ahah
    0.89
     envelop
    0.89
    POSITIVE LOGITS
    ম
    1.24
    jų
    1.23
     primeros
    1.20
     principales
    1.18
     danni
    1.17
    kumar
    1.16
    ्स
    1.16
     datos
    1.15
    ीय
    1.15
    wolves
    1.13
    Act Density 0.355%

    No Known Activations