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

    Neuronpedia

    INDEX
    Explanations

    watercolor painting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ע
    0.87
    0.86
    ا
    0.85
    ק
    0.84
    ун
    0.81
    ού
    0.80
     carbure
    0.78
     in
    0.77
     thermoplastic
    0.77
     základ
    0.75
    POSITIVE LOGITS
    ل
    0.91
    and
    0.82
    و
    0.78
    attempts
    0.75
    ↵↵
    0.71
    ;
    0.71
    clean
    0.70
    :
    0.70
    ade
    0.69
     اکنون
    0.68
    Act Density 0.001%

    No Known Activations