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

    Neuronpedia

    INDEX
    Explanations

    references to citations or academic sources

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

    citations or references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -1.02
    fjspx
    -0.58
    ########.
    -0.57
    onomía
    -0.57
     NgModule
    -0.56
    WebServlet
    -0.56
    DockStyle
    -0.55
    PyExc
    -0.53
    msgSender
    -0.53
    ftagPool
    -0.52
    POSITIVE LOGITS
    <sup>
    0.40
     hence
    0.39
     čast
    0.39
    .
    0.38
     ifølge
    0.36
     tyle
    0.35
     unless
    0.35
    Hence
    0.34
    CDCl
    0.34
     Hence
    0.34
    Act Density 0.074%

    No Known Activations