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

    Neuronpedia

    INDEX
    Explanations

    anything that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     buildTypes
    0.44
    なければ
    0.42
    筲
    0.42
     কর্তৃক
    0.42
    туре
    0.40
     దో
    0.39
    することは
    0.39
     이를
    0.38
    되는
    0.38
     associée
    0.37
    POSITIVE LOGITS
     isn
    1.08
     wasn
    1.03
     hasn
    0.94
     pertains
    0.88
     doesn
    0.86
     resembles
    0.85
     relates
    0.81
     involves
    0.79
     gets
    0.77
     belongs
    0.77
    Act Density 0.042%

    No Known Activations