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

    Neuronpedia

    INDEX
    Explanations

    frac

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    大きく
    -0.07
     нам
    -0.07
     exaggerated
    -0.07
    嚴重
    -0.07
     Tent
    -0.07
    𐤕
    -0.06
     XXX
    -0.06
    ᅡ
    -0.06
    yte
    -0.06
     ganze
    -0.06
    POSITIVE LOGITS
     Might
    0.08
     Shipping
    0.07
     ceased
    0.07
    Auto
    0.07
    ˦
    0.07
    .low
    0.07
    arial
    0.07
     Maison
    0.07
     richness
    0.07
    代言
    0.07
    Act Density 0.014%

    No Known Activations