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

    Neuronpedia

    INDEX
    Explanations

    DOCTYPE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     su
    -0.59
    وح
    -0.48
    Forget
    -0.46
     Try
    -0.44
     Lam
    -0.44
     sur
    -0.44
     sus
    -0.43
    ęs
    -0.43
    Try
    -0.43
    Lam
    -0.42
    POSITIVE LOGITS
    parsedMessage
    1.12
     ExecuteAsync
    0.90
    DebuggerNonUser
    0.88
     "..\..\..\
    0.80
    MessageTagHelper
    0.77
    writeFieldEnd
    0.77
     "..\..\
    0.76
    0.74
     iprot
    0.73
     CommonModule
    0.73
    Act Density 0.122%

    No Known Activations