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

    Neuronpedia

    INDEX
    Explanations

    hydro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    仙
    -0.07
     teenager
    -0.07
     Bieber
    -0.06
     Lone
    -0.06
    елен
    -0.06
    usalem
    -0.06
    perl
    -0.06
    Five
    -0.06
     lone
    -0.06
     kỷ
    -0.06
    POSITIVE LOGITS
     hydro
    0.09
     百度流量
    0.08
    机构
    0.07
    RD
    0.07
    συ
    0.07
     Hydro
    0.07
    )p
    0.07
     水
    0.07
    bro
    0.07
    )f
    0.07
    Act Density 0.016%

    No Known Activations