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

    Neuronpedia

    INDEX
    Explanations

    lists of names or codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aint
    0.41
     interview
    0.38
     የበለጠ
    0.37
    JUST
    0.37
     goatee
    0.37
     recently
    0.36
    iete
    0.36
     stout
    0.36
     informants
    0.36
     जेटली
    0.36
    POSITIVE LOGITS
     обра
    0.42
    ף
    0.41
    ப்புகள்
    0.40
     ont
    0.40
    𝒙
    0.40
     മി
    0.39
     明
    0.38
    msford
    0.37
     unim
    0.37
     स्टेटस
    0.37
    Act Density 0.000%

    No Known Activations