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

    Neuronpedia

    INDEX
    Explanations

    AI alignment and thought experiments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⼯
    0.59
    𝑬
    0.49
    য়ং
    0.48
    ,​
    0.47
    类似于
    0.47
    这也
    0.47
    混合
    0.47
    Mov
    0.46
    াকাছি
    0.46
    Werk
    0.46
    POSITIVE LOGITS
    ↵
    0.58
     publications
    0.45
    wiad
    0.43
    z
    0.43
     $
    0.42
    BlackElo
    0.42
     Transactions
    0.41
     sectarian
    0.41
     herald
    0.40
     turnout
    0.40
    Act Density 0.000%

    No Known Activations