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

    Neuronpedia

    INDEX
    Explanations

    qualifiers or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ️
    0.28
     &
    0.26
     tuttavia
    0.25
      
    0.25
     অথচ
    0.23
    '
    0.23
    ’
    0.23
     અને
    0.21
       
    0.21
     এবং
    0.21
    POSITIVE LOGITS
     with
    0.50
     עם
    0.46
     dengan
    0.45
     với
    0.38
     from
    0.37
    dengan
    0.37
     via
    0.37
     через
    0.36
     through
    0.35
     by
    0.34
    Act Density 0.134%

    No Known Activations