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

    Neuronpedia

    INDEX
    Explanations

    creating parent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ren
    0.75
     πι
    0.72
    fries
    0.69
     വേണ്ടി
    0.68
     মিলিয়ন
    0.68
     во
    0.68
     jendela
    0.68
    schod
    0.66
     կ
    0.66
     Greenwood
    0.65
    POSITIVE LOGITS
     also
    2.00
    also
    1.85
    Also
    1.55
     também
    1.54
    也
    1.54
     también
    1.53
     Also
    1.51
     també
    1.49
     aussi
    1.44
     også
    1.39
    Act Density 0.007%

    No Known Activations