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

    Neuronpedia

    INDEX
    Explanations

    many, various, or specific groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    1.02
     организм
    0.99
     відбувається
    0.98
    othesis
    0.98
    roep
    0.95
     venga
    0.95
     viene
    0.94
    画面
    0.94
    Propagation
    0.93
    这个人
    0.92
    POSITIVE LOGITS
     numerous
    2.53
     dozens
    2.44
     berbagai
    2.40
     다양한
    2.38
     numerosos
    2.36
     countless
    2.34
     birçok
    2.34
     zahlreichen
    2.31
    さまざまな
    2.31
     beragam
    2.30
    Act Density 1.037%

    No Known Activations