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

    Neuronpedia

    INDEX
    Explanations

    searching for keywords or text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Link
    0.42
     Channel
    0.41
     SRS
    0.41
     Off
    0.40
    макраты
    0.39
     SBS
    0.39
     कार्तिक
    0.37
     Loyalty
    0.37
     Slovakia
    0.36
     Flinders
    0.36
    POSITIVE LOGITS
    关键字
    0.51
    keywords
    0.49
     keywords
    0.46
    searchText
    0.46
     mentions
    0.45
    mention
    0.44
    searchview
    0.44
     searchText
    0.43
    containing
    0.43
    contains
    0.42
    Act Density 0.083%

    No Known Activations