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

    Neuronpedia

    INDEX
    Explanations

    Cooking instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avings
    -0.07
     Wenger
    -0.07
     births
    -0.07
     believers
    -0.06
     Pens
    -0.06
    beans
    -0.06
    ulu
    -0.06
     Cubs
    -0.06
    那个
    -0.06
     bloss
    -0.06
    POSITIVE LOGITS
    ,out
    0.08
    CharacterSet
    0.07
    Categoria
    0.07
     Required
    0.07
    ערה
    0.07
    𝐼
    0.07
    filtro
    0.07
     retorna
    0.07
    .findAll
    0.06
     listar
    0.06
    Act Density 0.005%

    No Known Activations