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

    Neuronpedia

    INDEX
    Explanations

    Availability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    刊
    -0.07
    atis
    -0.06
    .signals
    -0.06
     North
    -0.06
    113
    -0.06
    roadcast
    -0.06
    沿
    -0.06
     температу
    -0.06
     persu
    -0.06
     Out
    -0.06
    POSITIVE LOGITS
    ाह
    0.07
    реб
    0.07
    오
    0.06
     }),↵↵
    0.06
    =".$_
    0.06
    _optimizer
    0.06
     contrib
    0.06
     feasible
    0.06
    ,request
    0.06
    ']))↵
    0.06
    Act Density 0.027%

    No Known Activations