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

    Neuronpedia

    INDEX
    Explanations

    Terminating processes

    np_max-act · gemini-2.0-flash

    The neuron detects terms related to closing or terminating a resource or connection (e.g., “Close,” “close,” “quit,” “stop”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     мист
    -0.07
    UTTON
    -0.06
     pillars
    -0.06
    _MI
    -0.06
    getY
    -0.06
    /dom
    -0.06
     cred
    -0.06
     вже
    -0.06
     книги
    -0.06
     paraph
    -0.06
    POSITIVE LOGITS
    Although
    0.07
    _private
    0.06
     tournaments
    0.06
    ['<{
    0.06
     proficiency
    0.06
    Delay
    0.06
    ATIC
    0.06
     Checks
    0.06
    nk
    0.06
    entina
    0.06
    Act Density 0.015%

    No Known Activations