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

    Neuronpedia

    INDEX
    Explanations

    long history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    веден
    0.49
    мере
    0.49
     excepting
    0.47
    媜
    0.47
    শ্বর
    0.47
    旿
    0.47
    би
    0.47
     assignee
    0.47
     sentença
    0.46
    實在
    0.46
    POSITIVE LOGITS
    ↵
    0.55
    Ak
    0.55
    >>
    0.49
    Hold
    0.48
    Latest
    0.46
    Gas
    0.46
    =>
    0.46
    Fa
    0.46
    ac
    0.45
    Include
    0.45
    Act Density 0.001%

    No Known Activations