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

    Neuronpedia

    INDEX
    Explanations

    microstatesle PremierPeru, Ecuador

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sufficiency
    0.51
    olium
    0.50
    alim
    0.49
    arp
    0.48
    <unused1>
    0.47
     منظ
    0.47
    ید
    0.46
    <unused49>
    0.45
    assertions
    0.45
     заповед
    0.45
    POSITIVE LOGITS
     अगर
    0.54
     a
    0.54
     Christopher
    0.52
    {
    0.52
     Liebig
    0.51
     Bryn
    0.51
     Tier
    0.49
    У
    0.49
    पर
    0.49
     Turnbull
    0.49
    Act Density 0.000%

    No Known Activations