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

    Neuronpedia

    INDEX
    Explanations

    gain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    річ
    -0.07
     Refugee
    -0.06
    Camp
    -0.06
    	with
    -0.06
    ам
    -0.06
     Backpack
    -0.06
    าร
    -0.06
    .Button
    -0.06
     στρα
    -0.06
     घटन
    -0.06
    POSITIVE LOGITS
    Advertisement
    0.06
     إلا
    0.06
    _pemb
    0.06
    ĐT
    0.06
     warriors
    0.06
     acidic
    0.06
     naj
    0.06
    �
    0.06
    ","",
    0.06
    uiten
    0.06
    Act Density 0.643%

    No Known Activations