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

    Neuronpedia

    INDEX
    Explanations

    Curiosity and finding out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     besch
    -0.07
     Müz
    -0.06
    हल
    -0.06
    OffsetTable
    -0.06
     vh
    -0.06
     oppressed
    -0.06
     شکن
    -0.06
    .weixin
    -0.06
    entityManager
    -0.06
    由于
    -0.06
    POSITIVE LOGITS
    은
    0.06
     aspects
    0.06
    REG
    0.06
    domains
    0.06
     regimes
    0.06
     Decompiled
    0.06
     inbound
    0.06
     reinst
    0.06
    greg
    0.06
     날짜
    0.06
    Act Density 0.025%

    No Known Activations