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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    The neuron remains silent—it does not respond to any tokens and thus does not detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    SetFont
    -0.07
    في
    -0.07
    MOOTH
    -0.06
     Wak
    -0.06
     Device
    -0.06
    �y
    -0.06
    ур
    -0.06
     PAD
    -0.06
    िर
    -0.06
     پرد
    -0.06
    POSITIVE LOGITS
    Earn
    0.08
     occasionally
    0.06
     adapt
    0.06
     없다
    0.06
    -detail
    0.06
     static
    0.06
    _declaration
    0.06
     meetup
    0.06
     starter
    0.06
     groupe
    0.06
    Act Density 0.005%

    No Known Activations