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

    Neuronpedia

    INDEX
    Explanations

    explore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     суще
    -0.06
    _tok
    -0.06
    ))+
    -0.06
    chief
    -0.06
    agnet
    -0.06
    predicted
    -0.06
     necessary
    -0.06
    ant
    -0.06
    oste
    -0.06
     arguing
    -0.06
    POSITIVE LOGITS
     explored
    0.09
     explore
    0.08
     explores
    0.07
    APPED
    0.07
    days
    0.07
     참여
    0.07
    DECL
    0.06
    翻
    0.06
     exploring
    0.06
     Tavern
    0.06
    Act Density 0.007%

    No Known Activations