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

    Neuronpedia

    INDEX
    Explanations

    occurrences of programming syntax and structure

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

    return, oneof, specific keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.85
     estekak
    -0.79
    fjspx
    -0.74
    ="@+
    -0.72
    WithIOException
    -0.69
     jspb
    -0.64
    GTCX
    -0.61
    httphttps
    -0.61
     Infórmanos
    -0.60
    findpost
    -0.60
    POSITIVE LOGITS
     nuage
    0.40
     nuages
    0.39
    company
    0.38
     marbre
    0.38
    home
    0.36
    param
    0.34
    mod
    0.34
    modity
    0.32
    wer
    0.31
    Option
    0.31
    Act Density 0.001%

    No Known Activations