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

    Neuronpedia

    INDEX
    Explanations

    escaped characters used in strings, particularly quotes and backslashes

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

    Strings or code snippets

    np_acts-logits-general · gemini-2.0-flash

    quotes and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    geocode
    -0.93
     يتيمه
    -0.90
    følgelig
    -0.79
     berg
    -0.76
     Kości
    -0.75
    osc
    -0.75
    Longrightarrow
    -0.74
    Eres
    -0.72
    ádza
    -0.71
    YNC
    -0.70
    POSITIVE LOGITS
    "\
    1.07
    '\
    1.02
    >\
    1.02
    ('\
    1.01
    <<"\
    1.00
    :\
    1.00
    ("\
    0.96
     "\
    0.93
     \
    0.92
     "..\..\..\
    0.89
    Act Density 0.218%

    No Known Activations