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

    Neuronpedia

    INDEX
    Explanations

    models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HAND
    -0.07
     Lista
    -0.07
    	method
    -0.06
     hassle
    -0.06
    赶
    -0.06
     lọc
    -0.06
    fork
    -0.06
    raf
    -0.06
    .Menu
    -0.06
     한번
    -0.06
    POSITIVE LOGITS
     (_)
    0.07
    /i
    0.06
    +/
    0.06
                ↵
    0.06
     attravers
    0.06
    自动
    0.06
    .password
    0.06
    others
    0.06
    :Boolean
    0.06
     eğit
    0.06
    Act Density 0.048%

    No Known Activations