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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icias
    -0.07
    lyph
    -0.07
    .vertices
    -0.07
     number
    -0.07
    inia
    -0.07
     insect
    -0.07
     violently
    -0.07
     bears
    -0.06
    INK
    -0.06
     לפרטים
    -0.06
    POSITIVE LOGITS
    /views
    0.08
    ออกจาก
    0.07
    跟进
    0.07
     shel
    0.07
     Pall
    0.06
    带回
    0.06
    ,float
    0.06
    重返
    0.06
    的脚步
    0.06
     Carson
    0.06
    Act Density 0.028%

    No Known Activations