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

    Neuronpedia

    INDEX
    Explanations

    solving equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সুরে
    0.47
     sebagian
    0.46
    सीसीआई
    0.45
     лига
    0.45
    र्गन
    0.45
     disediakan
    0.45
    ૨
    0.44
    ெற்ற
    0.44
     गीत
    0.44
    诗
    0.43
    POSITIVE LOGITS
     To
    0.51
    probability
    0.47
    To
    0.46
     Extra
    0.46
     eng
    0.46
     将
    0.45
    Focus
    0.45
    ,
    0.45
     main
    0.44
     syn
    0.44
    Act Density 0.001%

    No Known Activations