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

    Neuronpedia

    INDEX
    Explanations

    DG

    np_max-act · gemini-2.0-flash

    This neuron primarily fires on uppercase abbreviations or acronyms (short all-caps tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    avr
    -0.08
    πη
    -0.07
    _coef
    -0.07
    EFA
    -0.07
     plasma
    -0.07
    IK
    -0.06
     merc
    -0.06
    �
    -0.06
    OMEM
    -0.06
    790
    -0.06
    POSITIVE LOGITS
     DN
    0.07
    >If
    0.07
     owning
    0.07
     FG
    0.06
    ằm
    0.06
     OW
    0.06
     JP
    0.06
     WS
    0.06
     MB
    0.06
     Sın
    0.06
    Act Density 0.195%

    No Known Activations