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

    Neuronpedia

    INDEX
    Explanations

    code and diagrams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ideally
    0.53
    Ideally
    0.46
     Ideally
    0.43
    oconut
    0.40
    nader
    0.40
    akum
    0.38
    ပါ။
    0.38
     inoculated
    0.38
     maximus
    0.38
     synced
    0.37
    POSITIVE LOGITS
     ذلك
    0.43
     comprend
    0.39
     justru
    0.38
     খোঁজ
    0.38
    잿
    0.38
    Dirty
    0.37
    dirty
    0.37
    Contributions
    0.37
     އަ
    0.37
    弊
    0.36
    Act Density 0.002%

    No Known Activations