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

    Neuronpedia

    INDEX
    Explanations

    -d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Brief
    -0.09
    erra
    -0.07
     Brief
    -0.07
    桥
    -0.07
     Neu
    -0.07
    戎
    -0.06
     JW
    -0.06
    _TRAIN
    -0.06
    中方
    -0.06
    甲
    -0.06
    POSITIVE LOGITS
    땀
    0.07
     волос
    0.07
    涌现
    0.07
    _sep
    0.07
    ]",
    0.07
     같은
    0.07
     �
    0.07
    ,/
    0.07
     Average
    0.06
     literacy
    0.06
    Act Density 0.000%

    No Known Activations