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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    The neuron detects directive names in text—i.e. keywords used to signal commands or headers such as HTTP header fields (“Expect”) or preprocessor directives (“define”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    桌
    -0.07
    -owner
    -0.07
     push
    -0.07
     sent
    -0.06
     џ
    -0.06
    avou
    -0.06
     Gambling
    -0.06
    .Build
    -0.06
    散
    -0.06
    CompatActivity
    -0.06
    POSITIVE LOGITS
     debian
    0.07
     alter
    0.07
     About
    0.06
    แม
    0.06
    λω
    0.06
     consequ
    0.06
    logger
    0.06
    	edit
    0.06
    (torch
    0.06
     Npgsql
    0.06
    Act Density 0.020%

    No Known Activations