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

    Neuronpedia

    INDEX
    Explanations

    giving information about explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apj
    0.46
    Whitespace
    0.45
    Estado
    0.44
     JAN
    0.44
    antad
    0.43
    Tuesday
    0.42
     jasmine
    0.42
    、『
    0.42
    ocurrencies
    0.42
    jub
    0.41
    POSITIVE LOGITS
    ة
    0.42
     ouvert
    0.40
     effet
    0.40
     М
    0.39
    бра
    0.39
     traf
    0.38
    ⿳
    0.38
     пола
    0.37
    لمانيا
    0.37
    hole
    0.37
    Act Density 1.542%

    No Known Activations