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

    Neuronpedia

    INDEX
    Explanations

    assessment and measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     investigation
    0.52
     discovery
    0.51
    discovery
    0.48
    添加
    0.47
    identification
    0.47
     investigations
    0.47
     descubrimiento
    0.46
     elucidation
    0.46
    adding
    0.46
    examination
    0.45
    POSITIVE LOGITS
     assess
    2.05
     Assess
    1.84
     assesses
    1.80
    Assess
    1.74
    assess
    1.72
     assessing
    1.68
     asses
    1.58
     Assessing
    1.57
     assessed
    1.56
     gauge
    1.55
    Act Density 0.033%

    No Known Activations