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

    Neuronpedia

    INDEX
    Explanations

    like, why, or what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ichage
    0.49
     abomin
    0.49
     espiritual
    0.47
     tecnológicas
    0.47
    ，《
    0.46
    ysław
    0.46
    はありません
    0.46
    irradiation
    0.46
     ദു
    0.46
     antigos
    0.45
    POSITIVE LOGITS
     I
    0.54
     Just
    0.48
     data
    0.46
     S
    0.46
     net
    0.45
     To
    0.45
     graph
    0.45
     output
    0.44
     p
    0.43
     group
    0.43
    Act Density 0.005%

    No Known Activations