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

    Neuronpedia

    INDEX
    Explanations

    well

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intuition
    -0.07
     너
    -0.07
    Mod
    -0.07
     يجب
    -0.06
     pants
    -0.06
    .warn
    -0.06
     firstly
    -0.06
     Opport
    -0.06
     Redirect
    -0.06
     оди
    -0.06
    POSITIVE LOGITS
    egen
    0.06
    jte
    0.06
    ']['
    0.06
     licensing
    0.06
    .Sql
    0.06
    orientation
    0.06
    орі
    0.06
    วรรณ
    0.06
     çalışma
    0.06
     nécess
    0.06
    Act Density 0.006%

    No Known Activations