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

    Neuronpedia

    INDEX
    Explanations

    time-bound goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    暠
    0.45
    㛣
    0.41
    ധിപ
    0.40
    尃
    0.39
     கலோரிகள்
    0.38
    airlines
    0.38
     sportsbook
    0.38
    AvlTree
    0.37
     পাকসেন
    0.37
     conductivity
    0.36
    POSITIVE LOGITS
    tand
    0.41
    lor
    0.40
    one
    0.39
    owed
    0.37
     anchored
    0.37
    Hal
    0.35
    date
    0.35
    entry
    0.35
     aspir
    0.35
    spers
    0.34
    Act Density 0.003%

    No Known Activations