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

    Neuronpedia

    INDEX
    Explanations

    explaining steps and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ش
    0.48
     abogados
    0.46
     News
    0.45
    法
    0.45
     Val
    0.44
     Punishment
    0.44
     Law
    0.43
     Cards
    0.43
    虧
    0.43
     đầu
    0.42
    POSITIVE LOGITS
    iloc
    0.48
     علامه
    0.46
     sapon
    0.46
     dispersive
    0.46
     clonal
    0.45
     countenance
    0.44
    andria
    0.44
    classe
    0.44
     pallet
    0.44
     spindle
    0.44
    Act Density 0.001%

    No Known Activations