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

    Neuronpedia

    INDEX
    Explanations

    salt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HOOK
    -0.07
    .topAnchor
    -0.06
    ,LOCATION
    -0.06
    .voice
    -0.06
     prescription
    -0.06
          ↵      ↵
    -0.06
     Ru
    -0.06
    Aaron
    -0.06
     "{}
    -0.06
    	ON
    -0.06
    POSITIVE LOGITS
    /App
    0.07
     Oriental
    0.06
    	pr
    0.06
    ιλ
    0.06
    BB
    0.06
    (DATA
    0.06
    ied
    0.06
    一切
    0.06
     와
    0.06
    ups
    0.06
    Act Density 0.004%

    No Known Activations