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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scale
    -0.07
    -sc
    -0.07
     Spieler
    -0.07
    破门
    -0.07
    مؤلف
    -0.06
    📡
    -0.06
     לצפיה
    -0.06
     ilaç
    -0.06
    apel
    -0.06
     ballo
    -0.06
    POSITIVE LOGITS
    /*/
    0.08
    ]->
    0.07
    Ờ
    0.07
    工作报告
    0.07
     xAxis
    0.07
    rite
    0.07
     widget
    0.07
    𝐤
    0.07
     NG
    0.07
     Regex
    0.07
    Act Density 0.000%

    No Known Activations