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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     עם
    -0.07
    汪
    -0.07
    你会发现
    -0.07
    -0.07
    鲜活
    -0.07
    andon
    -0.06
     dei
    -0.06
     stocking
    -0.06
     completo
    -0.06
    وحد
    -0.06
    POSITIVE LOGITS
    .DateTime
    0.07
     חד
    0.07
    quate
    0.07
    ayers
    0.07
    GV
    0.07
     Punjab
    0.07
     surged
    0.06
    (cc
    0.06
     Acer
    0.06
     cancelButton
    0.06
    Act Density 0.026%

    No Known Activations