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

    Neuronpedia

    INDEX
    Explanations

    product series names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ৃ
    0.46
     Indie
    0.42
     anecdotes
    0.40
     foaf
    0.39
    ॕ
    0.39
     jee
    0.38
     തവണ
    0.38
     `;
    0.38
    FreeFlag
    0.37
     じゃん
    0.37
    POSITIVE LOGITS
    S
    0.69
     series
    0.62
    series
    0.61
    R
    0.57
    系列
    0.56
    B
    0.56
     시리즈
    0.54
    P
    0.54
    Series
    0.53
    L
    0.53
    Act Density 0.044%

    No Known Activations