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

    Neuronpedia

    INDEX
    Explanations

    ym

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    氨基
    -0.08
    띤
    -0.07
     clad
    -0.07
    坐标
    -0.07
    вали
    -0.07
    Ether
    -0.07
    꽈
    -0.07
    勍
    -0.07
    なし
    -0.07
    큐
    -0.07
    POSITIVE LOGITS
     dokument
    0.08
    Preferences
    0.07
    eff
    0.07
    =S
    0.07
    后期
    0.07
     friendship
    0.07
     жидк
    0.07
     HAL
    0.06
    super
    0.06
     resolve
    0.06
    Act Density 0.001%

    No Known Activations