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

    Neuronpedia

    INDEX
    Explanations

    etric

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Watching
    -0.09
     microbes
    -0.09
     watching
    -0.08
     escalation
    -0.08
    Watching
    -0.08
     confr
    -0.08
     Quincy
    -0.08
     Sling
    -0.07
     Hezbollah
    -0.07
    culture
    -0.07
    POSITIVE LOGITS
     sinus
    0.09
    分别
    0.08
     વી
    0.08
    Separate
    0.08
     координ
    0.07
     separate
    0.07
     закона
    0.07
    كون
    0.07
     Скор
    0.07
    ulog
    0.07
    Act Density 0.004%

    No Known Activations