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

    Neuronpedia

    INDEX
    Explanations

    bias and data

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comuni
    0.69
     domes
    0.68
    都会
    0.65
    ্যালি
    0.65
     thumb
    0.65
     по
    0.63
     tram
    0.62
     prem
    0.62
     الس
    0.62
     Bai
    0.62
    POSITIVE LOGITS
    CPP
    0.75
    Muhammad
    0.72
    Cpp
    0.71
    yyati
    0.69
    Cele
    0.69
    Intel
    0.67
    Fig
    0.65
    Dar
    0.64
    芸能
    0.63
     CPP
    0.63
    Act Density 0.124%

    No Known Activations