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

    Neuronpedia

    INDEX
    Explanations

    end of lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ব
    1.79
    స్
    1.60
    م
    1.55
    IAL
    1.51
    ᖇ
    1.47
     respectivos
    1.47
    ஸ்
    1.45
    ן
    1.45
    ো
    1.44
    য
    1.41
    POSITIVE LOGITS
     feasible
    1.34
    ła
    1.33
    <>());
    1.29
    Kant
    1.26
     microtub
    1.25
     gens
    1.24
    $('#
    1.24
    reeze
    1.21
     seab
    1.21
     mucosa
    1.21
    Act Density 0.336%

    No Known Activations