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

    Neuronpedia

    INDEX
    Explanations

    balance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     primera
    -0.07
     Broken
    -0.07
    .getData
    -0.07
     Firstly
    -0.07
    YOUR
    -0.07
    acro
    -0.07
     Leer
    -0.07
    YK
    -0.06
     emerging
    -0.06
     gut
    -0.06
    POSITIVE LOGITS
     Balance
    0.07
    Interested
    0.07
     balance
    0.06
     influences
    0.06
     warranties
    0.06
     VE
    0.06
    τέ
    0.06
    "),
↵
    0.06
     abundance
    0.06
     emphasis
    0.06
    Act Density 0.005%

    No Known Activations