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

    Neuronpedia

    INDEX
    Explanations

    crafted, designed, featuring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     logins
    0.48
     кстати
    0.46
     bonus
    0.45
    밌
    0.44
     learnings
    0.44
    সুতরাং
    0.44
     progenitors
    0.43
    bonus
    0.42
    があるので
    0.42
    இதனால்
    0.42
    POSITIVE LOGITS
     Crafted
    0.80
     crafted
    0.75
     Featuring
    0.68
    crafted
    0.64
    Featuring
    0.64
     Created
    0.62
     Constructed
    0.58
    Created
    0.58
    Designed
    0.56
     Designed
    0.55
    Act Density 0.015%

    No Known Activations