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

    Neuronpedia

    INDEX
    Explanations

    multiple

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chocol
    -0.07
     Sz
    -0.07
    pager
    -0.06
     أ
    -0.06
     ιστο
    -0.06
    َأ
    -0.06
    羽
    -0.06
     표
    -0.06
    릿
    -0.06
     ون
    -0.06
    POSITIVE LOGITS
    Shutdown
    0.07
     destruct
    0.06
     telescope
    0.06
     onChange
    0.06
    MN
    0.06
    PLATFORM
    0.06
     kiểm
    0.06
    nginx
    0.06
     punch
    0.06
     pests
    0.06
    Act Density 0.002%

    No Known Activations