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

    Neuronpedia

    INDEX
    Explanations

    questions about procedures and methods in programming contexts

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

    asking how to configure or adjust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.56
     avoient
    -0.54
    protoimpl
    -0.53
     enfans
    -0.52
     mattino
    -0.50
    basicConfig
    -0.48
     mães
    -0.46
     andato
    -0.46
    UrlResolution
    -0.45
     BorderRadius
    -0.45
    POSITIVE LOGITS
     estekak
    0.41
     quelconque
    0.39
     vare
    0.38
    orghini
    0.36
     wirk
    0.36
    urtstag
    0.36
    uvwxyz
    0.35
     map
    0.35
     Bicycle
    0.35
     enough
    0.34
    Act Density 0.174%

    No Known Activations