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

    Neuronpedia

    INDEX
    Explanations

    system functionality and capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     agak
    0.89
     oldest
    0.89
     underrated
    0.87
    huge
    0.82
    orsanız
    0.82
    あなたが
    0.81
     vecchio
    0.80
    issime
    0.79
     famous
    0.78
     bastante
    0.78
    POSITIVE LOGITS
     integrates
    1.17
     utilizes
    1.03
     adapts
    1.01
     arrives
    1.00
     utilises
    0.97
     includes
    0.96
     incorporates
    0.94
     complies
    0.93
     equips
    0.93
     employs
    0.92
    Act Density 0.008%

    No Known Activations