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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zoals
    -0.07
    图
    -0.06
     world
    -0.06
    oming
    -0.06
    .startswith
    -0.06
    lek
    -0.06
    CA
    -0.06
     trung
    -0.06
     бра
    -0.06
     trộn
    -0.06
    POSITIVE LOGITS
     supported
    0.07
     ecstatic
    0.07
    stead
    0.06
     Elaine
    0.06
    /Delete
    0.06
    ？」
    0.06
    					↵					↵
    0.06
     extrem
    0.06
    _enqueue
    0.06
    elementGuidId
    0.06
    Act Density 0.220%

    No Known Activations