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

    Neuronpedia

    INDEX
    Explanations

    percentages and formatted numerical expressions

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

    Programming code and special characters

    np_acts-logits-general · gemini-2.0-flash

    variable formatting strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NavController
    -0.73
     typelib
    -0.69
    )':
    -0.61
    WAUKEE
    -0.61
     незавершена
    -0.61
    WindowConstants
    -0.60
     mukana
    -0.60
    }');
    -0.60
    >");
    -0.60
    }`);
    -0.59
    POSITIVE LOGITS
    tető
    0.51
     terminator
    0.47
     ['$
    0.46
    raborty
    0.46
     IPX
    0.46
     Printing
    0.46
    ensement
    0.45
    нциклопедия
    0.45
    ceiro
    0.43
    lencia
    0.43
    Act Density 0.328%

    No Known Activations