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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash

    This neuron never responds to any token—i.e. it’s effectively “dead” and does not detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ALIGN
    -0.07
     سالم
    -0.07
     світу
    -0.07
    <Game
    -0.07
     robotic
    -0.06
    .def
    -0.06
     defendants
    -0.06
    \">↵
    -0.06
     Defendants
    -0.06
    .acquire
    -0.06
    POSITIVE LOGITS
    チャ
    0.06
    ramid
    0.06
     Za
    0.06
    aton
    0.06
     hadde
    0.06
     Comet
    0.06
    omap
    0.06
     mistakenly
    0.06
    agram
    0.06
    шиб
    0.05
    Act Density 0.002%

    No Known Activations