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

    Neuronpedia

    INDEX
    Explanations

    down

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getVersion
    -0.07
     作
    -0.06
     picks
    -0.06
    cec
    -0.06
    رفت
    -0.06
     ΕΠ
    -0.06
     Tells
    -0.06
     nilai
    -0.06
    .getOrder
    -0.06
    をつ
    -0.06
    POSITIVE LOGITS
     shutdown
    0.09
     lockdown
    0.08
     Shutdown
    0.08
    shutdown
    0.07
    .shutdown
    0.07
    DOWN
    0.07
    Sending
    0.07
    рив
    0.06
    /)↵
    0.06
    /disable
    0.06
    Act Density 0.003%

    No Known Activations