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

    Neuronpedia

    INDEX
    Explanations

    language dealing with political tensions surrounding health

    oai_token-act-pair · gemini-2.0-flash

    Scientific/Medical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jegy
    -0.66
     hyö
    -0.65
     sähkö
    -0.65
     henkil
    -0.63
     øns
    -0.63
     žem
    -0.62
     dår
    -0.61
     mør
    -0.61
     väli
    -0.61
     néz
    -0.60
    POSITIVE LOGITS
    I
    0.58
     a
    0.57
     bezeichneter
    0.54
     الحره
    0.54
     scn
    0.52
    UnusedPrivate
    0.51
    setVerticalGroup
    0.51
     hie
    0.51
     tew
    0.50
    a
    0.50
    Act Density 25.661%

    No Known Activations