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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash

    This neuron activates on descriptions of reading an entire file’s contents into a string (e.g., use of `read()` to load a file into a string variable).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sliced
    -0.07
     rotational
    -0.07
     Πο
    -0.07
     سازی
    -0.07
    Tor
    -0.06
     Preservation
    -0.06
     BR
    -0.06
    Mar
    -0.06
    melon
    -0.06
     GAR
    -0.06
    POSITIVE LOGITS
    Scanner
    0.07
     ([]
    0.07
     كنت
    0.06
     pornografia
    0.06
     öne
    0.06
     looph
    0.06
    .toArray
    0.06
     což
    0.06
    _outline
    0.06
    iyorum
    0.06
    Act Density 0.022%

    No Known Activations