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

    Neuronpedia

    INDEX
    Explanations

    cruise lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ayı
    0.54
     compon
    0.52
    with
    0.51
    獻
    0.50
    muster
    0.48
     comand
    0.47
     recursion
    0.46
    စေ
    0.46
     esprim
    0.46
    la
    0.45
    POSITIVE LOGITS
    дена
    0.56
    Ko
    0.52
    KINS
    0.51
    KIS
    0.51
    د
    0.50
    Kwa
    0.49
    Qual
    0.48
    Cruise
    0.48
    PCS
    0.48
    ्रीट
    0.48
    Act Density 0.000%

    No Known Activations