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

    Neuronpedia

    INDEX
    Explanations

    people by interest or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     serez
    0.35
     could
    0.34
     oppure
    0.34
     seraient
    0.34
     questi
    0.34
    could
    0.34
     probabilmente
    0.33
     pourraient
    0.33
     pequenos
    0.33
     são
    0.33
    POSITIVE LOGITS
     trying
    0.44
     analyzing
    0.37
    进行的
    0.35
    竭
    0.34
    trying
    0.34
     사용하는
    0.33
    Trying
    0.32
     bezig
    0.31
    将
    0.31
     seeking
    0.31
    Act Density 0.027%

    No Known Activations