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

    Neuronpedia

    INDEX
    Explanations

    financial implications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ש
    0.49
    itif
    0.47
    wirtschaft
    0.45
    ਸ
    0.45
     할인
    0.44
     navigate
    0.44
     బ్రిటిషు
    0.44
    వైపు
    0.44
    м
    0.43
    চ
    0.43
    POSITIVE LOGITS
     Creativity
    0.44
     Shame
    0.43
     HOWEVER
    0.42
     l
    0.42
     inan
    0.42
     Expectations
    0.42
     recorded
    0.41
     were
    0.40
     bloodshed
    0.40
     Recorded
    0.40
    Act Density 0.006%

    No Known Activations