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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eş
    -0.07
    head
    -0.07
     Presents
    -0.06
     duct
    -0.06
    NP
    -0.06
    учас
    -0.06
    μένα
    -0.06
    ら
    -0.06
    領
    -0.06
    /card
    -0.06
    POSITIVE LOGITS
     opportun
    0.07
    Dyn
    0.07
     était
    0.06
     الخارج
    0.06
    Dat
    0.06
    OwnerId
    0.06
     nebude
    0.06
     zeměděl
    0.06
     resemble
    0.06
    ircon
    0.06
    Act Density 0.029%

    No Known Activations