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

    Neuronpedia

    INDEX
    Explanations

    huggingface pipeline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aj
    0.76
    ți
    0.74
     tissue
    0.72
     cheeks
    0.72
    Rais
    0.72
     rosemary
    0.70
     compelling
    0.70
     EE
    0.69
     publicity
    0.69
     politely
    0.69
    POSITIVE LOGITS
    huge
    1.26
    cled
    1.25
    凄
    1.21
    bikes
    1.17
     vse
    1.15
    গ্রস্থ
    1.15
     व्हाउचर
    1.14
     amplo
    1.13
     会
    1.13
     grosses
    1.13
    Act Density 0.012%

    No Known Activations