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

    Neuronpedia

    INDEX
    Explanations

    study and research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Reporting
    0.44
     Placing
    0.44
    所示
    0.44
    Purch
    0.43
    кса
    0.43
    Ко
    0.42
     placing
    0.42
     tỷ
    0.41
    Shelf
    0.41
     Coaches
    0.41
    POSITIVE LOGITS
    political
    0.49
    _{\
    0.47
    ovať
    0.45
     ছোট
    0.42
     atmospheric
    0.41
     devolution
    0.39
     januar
    0.39
    ranging
    0.39
     revanche
    0.38
     coalesce
    0.38
    Act Density 0.010%

    No Known Activations