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

    Neuronpedia

    INDEX
    Explanations

    claim

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     endowments
    1.15
     infusions
    1.15
     contingency
    1.13
     drawers
    1.11
     gratifying
    1.11
    кции
    1.10
     expectancy
    1.10
     மாசுபடுத்த
    1.08
    loride
    1.08
     contingencies
    1.08
    POSITIVE LOGITS
    आप
    1.11
    o
    1.00
    Tá
    0.98
    est
    0.97
    \%$
    0.96
     terminó
    0.94
    मैं
    0.94
    دان
    0.91
     avea
    0.89
     Każ
    0.87
    Act Density 0.018%

    No Known Activations