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

    Neuronpedia

    INDEX
    Explanations

    data storage and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    創業
    0.48
    genheim
    0.46
    echolog
    0.44
    DanhMucSP
    0.43
     ['*.
    0.43
     gstlal
    0.42
    nameSort
    0.42
    濘
    0.42
    ಗಾರ
    0.42
    addKill
    0.42
    POSITIVE LOGITS
     values
    0.65
     execution
    0.64
     specified
    0.55
     Execution
    0.54
     represented
    0.52
     executed
    0.52
     executes
    0.52
     automatically
    0.52
     specifies
    0.52
     mechanism
    0.52
    Act Density 0.184%

    No Known Activations