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

    Neuronpedia

    INDEX
    Explanations

    Website snippets and instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﻮ
    -0.07
    >Loading
    -0.07
    招
    -0.07
     אלו
    -0.07
    幪
    -0.07
    对应
    -0.07
    保鲜
    -0.07
    >this
    -0.07
    加持
    -0.06
    Are
    -0.06
    POSITIVE LOGITS
    Sea
    0.08
    ﳫ
    0.07
     commented
    0.07
     destac
    0.07
    -null
    0.07
     semanas
    0.07
    히
    0.07
     Nullable
    0.06
     trimest
    0.06
    波动
    0.06
    Act Density 0.071%

    No Known Activations