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

    Neuronpedia

    INDEX
    Explanations

    comma before and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wears
    0.61
     pacif
    0.57
     shops
    0.55
     कॉलेज
    0.55
     Piero
    0.54
     Primeiro
    0.53
     wearing
    0.52
     Olivia
    0.52
     Isaiah
    0.52
     grumpy
    0.52
    POSITIVE LOGITS
    pronged
    0.57
    position
    0.56
    s
    0.52
    terminated
    0.50
    вна
    0.49
    grained
    0.48
    text
    0.47
    flavor
    0.47
    simply
    0.47
    visual
    0.46
    Act Density 0.000%

    No Known Activations