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

    Neuronpedia

    INDEX
    Explanations

    introduces explanations or agendas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    끄
    0.51
    น
    0.48
    ολ
    0.47
    тости
    0.46
    児童
    0.45
    セ
    0.44
     resistive
    0.43
    釈
    0.43
    Ὀ
    0.42
    esity
    0.42
    POSITIVE LOGITS
    who
    0.50
     anno
    0.47
     Ramadan
    0.46
     Alberta
    0.46
     carreira
    0.46
     spectacularly
    0.46
     früher
    0.46
     Calgary
    0.45
     Ana
    0.45
     Praia
    0.45
    Act Density 0.001%

    No Known Activations