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

    Neuronpedia

    INDEX
    Explanations

    strings and formatted outputs in code-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    string formatting and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "..\..\
    -0.34
    contrar
    -0.33
     EdgeInsets
    -0.33
     resourceCulture
    -0.33
    AccessorTable
    -0.32
    Autoritní
    -0.30
    نجليز
    -0.30
    Chham
    -0.30
     będziemy
    -0.29
    Rhestr
    -0.28
    POSITIVE LOGITS
    ftagPool
    0.55
     canlynol
    0.54
    writeFieldEnd
    0.54
    enumii
    0.51
    rifuge
    0.50
    fjspx
    0.50
     समीक्षक
    0.50
     deſſen
    0.50
     unſer
    0.50
    WriteTagHelper
    0.48
    Act Density 0.009%

    No Known Activations