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

    Neuronpedia

    INDEX
    Explanations

    github

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    行业
    -0.07
    xd
    -0.07
    350
    -0.07
     tox
    -0.07
     bilingual
    -0.07
    otr
    -0.06
    ório
    -0.06
    .Compute
    -0.06
    ота
    -0.06
    원을
    -0.06
    POSITIVE LOGITS
     Redistribution
    0.06
     GK
    0.06
     bypass
    0.06
     Mn
    0.06
     abandoning
    0.06
     founders
    0.06
     overdose
    0.06
     пок
    0.06
     BFS
    0.06
     ain
    0.06
    Act Density 0.001%

    No Known Activations