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

    Neuronpedia

    INDEX
    Explanations

    theory

    np_max-act · gemini-2.0-flash

    The neuron activates whenever the text is talking about the string‐theory framework in physics.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sided
    -0.06
    _CREATE
    -0.06
     Playstation
    -0.06
    出版社
    -0.06
    ورية
    -0.06
    สด
    -0.05
     potency
    -0.05
     diligently
    -0.05
    planation
    -0.05
    іх
    -0.05
    POSITIVE LOGITS
    rawer
    0.07
    érer
    0.07
    illa
    0.07
    ILLA
    0.07
    urret
    0.06
     nev
    0.06
    taient
    0.06
    .move
    0.06
    ويت
    0.06
     Bloody
    0.06
    Act Density 0.017%

    No Known Activations