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

    Neuronpedia

    INDEX
    Explanations

    Douglas Adams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     natomiast
    0.49
    agra
    0.45
     Tennyson
    0.45
    warl
    0.45
     Obituary
    0.45
    iana
    0.45
    igr
    0.44
    HARAD
    0.44
     indefinitely
    0.44
     Yon
    0.44
    POSITIVE LOGITS
    ាប់
    0.54
    ح
    0.52
    리
    0.52
    ки
    0.51
    ку
    0.49
    已
    0.49
    άζ
    0.48
    دين
    0.47
    涷
    0.47
    ताच
    0.47
    Act Density 0.000%

    No Known Activations