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

    Neuronpedia

    INDEX
    Explanations

    IDI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NAMES
    -0.06
     bog
    -0.06
     Auch
    -0.06
     你
    -0.06
     Auschwitz
    -0.05
    ción
    -0.05
    holm
    -0.05
    Until
    -0.05
    ktor
    -0.05
    信
    -0.05
    POSITIVE LOGITS
    ев
    0.07
    距离
    0.07
     thỏa
    0.06
    91
    0.06
     iş
    0.06
    weights
    0.06
     Position
    0.06
     swollen
    0.06
    leşik
    0.06
    ेच
    0.06
    Act Density 0.000%

    No Known Activations