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

    Neuronpedia

    INDEX
    Explanations

    closure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cavity
    -0.07
     analytic
    -0.07
    憩
    -0.07
     Est
    -0.07
    .det
    -0.06
    룄
    -0.06
    ው
    -0.06
    を与え
    -0.06
    管理工作
    -0.06
     finest
    -0.06
    POSITIVE LOGITS
    hton
    0.07
     dific
    0.07
    urr
    0.07
    CLOSE
    0.07
    _TRAIN
    0.07
     том
    0.07
    premium
    0.07
    /remove
    0.07
    /std
    0.07
    增加
    0.06
    Act Density 0.002%

    No Known Activations