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

    Neuronpedia

    INDEX
    Explanations

    risks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ankles
    -0.07
    _tag
    -0.07
     τά
    -0.06
    strstr
    -0.06
    iếu
    -0.06
     Goods
    -0.06
     avenue
    -0.06
    ากร
    -0.06
     whose
    -0.06
    CBC
    -0.06
    POSITIVE LOGITS
    .Completed
    0.07
    Large
    0.07
    �
    0.07
    -centric
    0.06
     Promo
    0.06
    ard
    0.06
     trope
    0.06
     Typography
    0.06
     corpus
    0.06
    uellement
    0.06
    Act Density 0.001%

    No Known Activations