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

    Neuronpedia

    INDEX
    Explanations

    splitting text segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ورح
    0.41
     موجودگی
    0.40
     Nus
    0.39
    த
    0.39
    alui
    0.38
     externo
    0.37
     രംഗ
    0.37
     memudahkan
    0.37
     configuración
    0.37
     బయ
    0.37
    POSITIVE LOGITS
     將
    0.39
     dismantling
    0.39
     将
    0.38
     doings
    0.37
    淪
    0.36
    鎶
    0.36
    獗
    0.36
    將
    0.35
    籮
    0.35
     dissection
    0.35
    Act Density 0.000%

    No Known Activations