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

    Neuronpedia

    INDEX
    Explanations

    close-up or proximity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ))){
    0.44
    )"))
    0.39
     Kame
    0.38
     クリ
    0.38
    ';"+
    0.37
    sas
    0.37
     ভালোবাসি
    0.37
    ='{{
    0.37
     苏
    0.37
     Cr
    0.36
    POSITIVE LOGITS
     proximity
    1.09
    proximity
    0.92
     close
    0.89
     closeness
    0.86
     closely
    0.81
    close
    0.79
     closer
    0.77
     proxim
    0.75
     близь
    0.74
     Close
    0.70
    Act Density 0.016%

    No Known Activations