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

    Neuronpedia

    INDEX
    Explanations

    it help, Freedom &

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Oh
    0.76
     ফিল্ম
    0.74
    Women
    0.71
    suggest
    0.68
    Wire
    0.68
    Jeg
    0.68
     महिले
    0.68
    Insights
    0.67
     கல்ல
    0.67
    Collider
    0.67
    POSITIVE LOGITS
    AnchorStyles
    0.78
     Integrative
    0.76
     optimizations
    0.74
     pengurangan
    0.74
    ત્રો
    0.74
     diterima
    0.70
    ყოფ
    0.69
     Modo
    0.68
    ಂತರ
    0.67
    zczeg
    0.67
    Act Density 0.000%

    No Known Activations