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

    Neuronpedia

    INDEX
    Explanations

    ensitivity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mé
    -0.07
    edith
    -0.06
     Bever
    -0.06
     Armor
    -0.06
     налог
    -0.06
    ��
    -0.06
     při
    -0.06
    ้องน
    -0.06
    ẳn
    -0.06
     cette
    -0.06
    POSITIVE LOGITS
    <?↵
    0.07
     října
    0.06
     viewWillAppear
    0.06
     blacks
    0.06
    Heap
    0.06
     Thread
    0.06
     rulings
    0.06
     concatenate
    0.06
    .placeholder
    0.06
    <?
    0.06
    Act Density 0.110%

    No Known Activations