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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tep
    -0.08
     mediaPlayer
    -0.07
     mulher
    -0.07
    телем
    -0.07
     seul
    -0.07
     tweets
    -0.07
    Freq
    -0.06
    ogr
    -0.06
     alcuni
    -0.06
    ߎ
    -0.06
    POSITIVE LOGITS
    锴
    0.07
     أسبوع
    0.07
    城堡
    0.07
    服务机构
    0.07
    PDO
    0.07
     databases
    0.07
     reversing
    0.07
    才行
    0.07
     exchanging
    0.07
    NP
    0.06
    Act Density 0.010%

    No Known Activations