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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    Behind
    -0.06
    áng
    -0.06
    agar
    -0.06
    任
    -0.06
    :{↵
    -0.06
    èn
    -0.06
    éli
    -0.06
     été
    -0.06
    pedia
    -0.06
    POSITIVE LOGITS
    ️
    0.07
     повинна
    0.07
    /card
    0.06
     prere
    0.06
    	page
    0.06
    882
    0.06
     Flake
    0.06
     ￣
    0.06
    .digest
    0.06
     dağ
    0.06
    Act Density 0.006%

    No Known Activations