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

    Neuronpedia

    INDEX
    Explanations

    IRA, APR, cru

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⦕
    0.49
    itag
    0.48
     Grâce
    0.48
    0.47
    )}_{\
    0.47
     marts
    0.47
     autonom
    0.47
    抂
    0.47
     चाह
    0.46
    读者
    0.45
    POSITIVE LOGITS
    ↵↵
    0.56
    5
    0.52
    0.49
     Ric
    0.48
    Horizontal
    0.47
    4
    0.45
     horizontal
    0.44
    un
    0.44
    cz
    0.44
     consistently
    0.43
    Act Density 0.001%

    No Known Activations