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

    Neuronpedia

    INDEX
    Explanations

    there are tons of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     truly
    0.75
     πραγμα
    0.74
     really
    0.72
    真正
    0.69
     कैरी
    0.69
    arıyla
    0.68
     officially
    0.67
     comfy
    0.67
     realmente
    0.67
     carab
    0.67
    POSITIVE LOGITS
     Occurrence
    0.79
     occurrence
    0.79
    occurrence
    0.76
    浠
    0.75
     lies
    0.73
     shuts
    0.72
     ocorre
    0.70
    เกิด
    0.69
     arises
    0.67
     occurs
    0.67
    Act Density 0.009%

    No Known Activations