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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     εμπ
    -0.07
     suất
    -0.07
     اند
    -0.06
     微
    -0.06
    ournée
    -0.06
    FindBy
    -0.06
    ApiKey
    -0.06
     CommandType
    -0.05
    tti
    -0.05
    .UltraWin
    -0.05
    POSITIVE LOGITS
     internship
    0.07
     {↵
    0.07
     sociology
    0.07
    (ro
    0.06
    ریم
    0.06
     underground
    0.06
     iy
    0.06
     și
    0.06
    urning
    0.06
    Host
    0.06
    Act Density 0.001%

    No Known Activations