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

    Neuronpedia

    INDEX
    Explanations

    Paulo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rett
    -0.08
    安检
    -0.07
     vars
    -0.07
    Redirect
    -0.07
     addict
    -0.07
     Extract
    -0.06
     KEEP
    -0.06
    럽
    -0.06
    ateurs
    -0.06
    ICK
    -0.06
    POSITIVE LOGITS
     KG
    0.07
    _scalar
    0.07
    .responses
    0.07
    什么事情
    0.07
    yclerView
    0.07
     Davidson
    0.06
    _SWAP
    0.06
    换成
    0.06
    ThanOrEqualTo
    0.06
    再加上
    0.06
    Act Density 0.014%

    No Known Activations