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

    Neuronpedia

    INDEX
    Explanations

    chains as sequences of calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Elon
    0.39
    доби
    0.39
    LONG
    0.38
     расходов
    0.37
    Rim
    0.37
    Plugin
    0.37
     ሽፋን
    0.36
    ImagePath
    0.36
    涼
    0.36
    бар
    0.36
    POSITIVE LOGITS
     call
    0.43
     chains
    0.42
     Call
    0.41
     string
    0.41
     thoughtfully
    0.40
     language
    0.40
     Gọi
    0.37
     callous
    0.37
     com
    0.36
     output
    0.36
    Act Density 0.010%

    No Known Activations