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

    Neuronpedia

    INDEX
    Explanations

    "if, then" advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     практи
    -0.07
    ývá
    -0.07
    imps
    -0.07
    톤
    -0.07
    š
    -0.07
    ког
    -0.06
     vysvět
    -0.06
     comparator
    -0.06
    chmod
    -0.06
     voksne
    -0.06
    POSITIVE LOGITS
     noticeable
    0.06
     총
    0.06
    -wrapper
    0.06
     disagree
    0.06
    ώσεις
    0.06
    ámara
    0.06
     вз
    0.06
    .Not
    0.06
    entario
    0.06
    uel
    0.06
    Act Density 0.041%

    No Known Activations