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

    Neuronpedia

    INDEX
    Explanations

    planned

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     age
    0.72
     sir
    0.65
    estern
    0.63
     un
    0.62
    putBoolean
    0.62
     Hir
    0.60
    Ping
    0.60
     wikipedia
    0.60
     Ender
    0.59
     anda
    0.58
    POSITIVE LOGITS
    oreal
    0.77
    iese
    0.74
     cotisation
    0.74
    墘
    0.73
     compétence
    0.73
    lessis
    0.73
    嵘
    0.71
     nucleation
    0.71
    ጦ
    0.71
     त्यौ
    0.70
    Act Density 0.004%

    No Known Activations