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

    Neuronpedia

    INDEX
    Explanations

    machines and mechanics

    np_max-act · gemini-2.0-flash

    the neuron activates on words related to batteries and recharging (e.g. “battery,” “batteries,” “recharge,” “recharger,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ơn
    -0.07
    坐
    -0.07
    artial
    -0.07
    たち
    -0.06
    StackTrace
    -0.06
     근
    -0.06
     Ark
    -0.06
    職
    -0.06
    462
    -0.06
    ，把
    -0.06
    POSITIVE LOGITS
     cavity
    0.07
    spr
    0.07
    Contents
    0.07
     »,
    0.07
    .getToken
    0.06
    abyte
    0.06
     в
    0.06
    verte
    0.06
     tokenId
    0.06
    pollo
    0.06
    Act Density 0.063%

    No Known Activations