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

    Neuronpedia

    INDEX
    Explanations

    summarizing key differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     càng
    0.77
    ançais
    0.77
     (/
    0.77
     grossly
    0.75
    laug
    0.74
     net
    0.73
     supremacist
    0.73
     TLS
    0.72
     monomers
    0.72
     MFC
    0.71
    POSITIVE LOGITS
    యో
    0.72
    |
    0.66
     mengatur
    0.62
    Syn
    0.62
    จักร
    0.61
     كرد
    0.60
    adhesive
    0.60
    ----------
    0.59
    |$.
    0.59
    Youtube
    0.59
    Act Density 0.051%

    No Known Activations