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

    Neuronpedia

    INDEX
    Explanations

    controls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    spirator
    0.41
    edar
    0.40
     Tibetan
    0.39
     sod
    0.39
    aj
    0.38
    יין
    0.38
     Assim
    0.38
    scaler
    0.37
     Ronnie
    0.37
     Sod
    0.37
    POSITIVE LOGITS
    Controls
    0.52
    controls
    0.50
     controls
    0.48
     Controls
    0.44
    ..");
    0.41
    パーツ
    0.40
     controles
    0.40
    Holds
    0.39
    Kamol
    0.38
     trusts
    0.37
    Act Density 0.000%

    No Known Activations