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

    Neuronpedia

    INDEX
    Explanations

    File extensions and web addresses

    np_max-act · gemini-2.0-flash

    The neuron chiefly activates on bits of source‐code or resource file path strings—i.e. file names with extensions (like `.py`, `.vala`, `.ui`, etc.) often coupled with slashes and line‐number colons.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     endorsing
    -0.07
    shaled
    -0.07
    Except
    -0.06
     протягом
    -0.06
    _THEME
    -0.06
     tentang
    -0.06
    Qualified
    -0.06
     Scient
    -0.06
     forfe
    -0.06
    ncmp
    -0.06
    POSITIVE LOGITS
     �
    0.07
    �
    0.07
    婚
    0.06
    0.06
    /json
    0.06
     Libya
    0.06
     KE
    0.06
     Vatican
    0.06
    _u
    0.06
     Cloud
    0.06
    Act Density 0.001%

    No Known Activations