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

    Neuronpedia

    INDEX
    Explanations

    predicting usage with tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     upay
    1.27
     Reporter
    1.23
     速
    1.18
    dler
    1.17
    ダー
    1.17
     Buses
    1.17
    اج
    1.16
     Eust
    1.15
     Newspapers
    1.14
     lorry
    1.14
    POSITIVE LOGITS
     with
    2.13
    with
    1.96
     WITH
    1.88
     dengan
    1.71
    With
    1.68
     avec
    1.67
     without
    1.60
     With
    1.59
    avec
    1.55
     với
    1.51
    Act Density 1.208%

    No Known Activations