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

    Neuronpedia

    INDEX
    Explanations

    open source

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    quia
    0.57
    versa
    0.56
    methylation
    0.56
    UQ
    0.55
    computed
    0.54
     терпе
    0.54
    infect
    0.54
    Leaf
    0.54
     कहला
    0.54
    quisa
    0.54
    POSITIVE LOGITS
     frontend
    0.61
     økonom
    0.59
     facade
    0.57
     klient
    0.57
     धीरे
    0.56
     arbeid
    0.56
     пово
    0.55
     takim
    0.55
     Rode
    0.54
     caster
    0.54
    Act Density 0.000%

    No Known Activations