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

    Neuronpedia

    INDEX
    Explanations

    each and every

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IDGE
    0.55
    塞尔
    0.54
    ل
    0.52
     Aware
    0.51
    VING
    0.51
    ケット
    0.50
    IFI
    0.50
    IVING
    0.49
    UTICAL
    0.49
    ⓵
    0.49
    POSITIVE LOGITS
     que
    0.57
     fueran
    0.54
     generalmente
    0.54
     preference
    0.52
     व
    0.51
    şi
    0.50
     જુ
    0.49
    scale
    0.49
     lograr
    0.48
    preferably
    0.48
    Act Density 0.000%

    No Known Activations