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

    Neuronpedia

    INDEX
    Explanations

    multilingual content or specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ម្
    1.02
    urement
    0.92
    linkedin
    0.90
     Achilles
    0.83
     brid
    0.82
     Geb
    0.81
     GABA
    0.81
     lac
    0.80
    fare
    0.79
     adc
    0.79
    POSITIVE LOGITS
    それぞれ
    2.04
     respectivamente
    1.97
     respectively
    1.92
    respectively
    1.75
    それぞれの
    1.72
     respectivement
    1.71
     각각
    1.71
     යන
    1.57
     jeweils
    1.55
    いずれ
    1.55
    Act Density 0.411%

    No Known Activations