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

    Neuronpedia

    INDEX
    Explanations

    causation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ariant
    -0.07
     forums
    -0.07
    であ
    -0.06
    ารย
    -0.06
     Company
    -0.06
    احت
    -0.06
    endpoint
    -0.06
    ชาต
    -0.06
    alignment
    -0.06
    Company
    -0.06
    POSITIVE LOGITS
     Mitsubishi
    0.06
     protagon
    0.06
    _Word
    0.06
     takson
    0.06
    .gallery
    0.06
    рей
    0.06
    Intialized
    0.06
     Atmos
    0.06
     там
    0.06
     Blast
    0.06
    Act Density 0.025%

    No Known Activations