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

    Neuronpedia

    INDEX
    Explanations

    countries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    營
    -0.07
     очередь
    -0.06
     spikes
    -0.06
    _caps
    -0.06
     повинен
    -0.06
    54
    -0.06
    55
    -0.06
     neurotrans
    -0.06
    purchase
    -0.06
    reachable
    -0.06
    POSITIVE LOGITS
    /=
    0.08
    %%↵
    0.07
    ]
↵
↵
    0.07
    ────
    0.07
    ']=
    0.07
    ;.
    0.07
    ariat
    0.06
    \""
    0.06
    "P
    0.06
     мал
    0.06
    Act Density 0.034%

    No Known Activations