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

    Neuronpedia

    INDEX
    Explanations

    descriptions of groups or entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     memberships
    0.46
     membership
    0.46
     diversion
    0.45
    ري
    0.44
    術
    0.44
    س
    0.44
    لیفون
    0.43
     lake
    0.43
     Referee
    0.42
    ریان
    0.42
    POSITIVE LOGITS
     মাঝারি
    0.48
     இப்பட
    0.48
     בת
    0.46
     অতি
    0.45
    orthodox
    0.45
    cripts
    0.44
    dataIn
    0.44
     уров
    0.43
     пода
    0.42
    invocation
    0.42
    Act Density 0.005%

    No Known Activations